Archives: WP version of published papers
 A OneCovariate at a Time, Multiple Testing Approach to Variable Selection in HighDimensional Linear Regression Models, by Alexander Chudik, George Kapetanios and M. Hashem Pesaran, February 2016, revised November 2016
 To Pool or not to Pool: Revisited, by M. Hashem Pesaran and Qiankun Zhou, forthcoming in Oxford Bulletin of Economics and Statistics, October 2017
 Testing for Alpha in Linear Factor Pricing Models with a Large Number of Securities, by M. Hashem Pesarann and Takashi Yamagata, March 2017
 HalfPanel Jackknife Fixed Effects Estimation of Panels with Weakly Exogenous Regressors, by Alexander Chudik, M. Hashem Pesarann and JuiChung Yang, SSRN Working Paper No. 281, September 2016
 Counterfactual Analysis in Macroeconometrics: An Empirical Investigation into the Effects of Quantitative Easing, by M. Hashem Pesaran and Ron P Smith, IZA Discussion Paper No. 6618, May 2012, revised June 2014
 Oil Prices and the Global Economy: Is It Different This Time Around?, by Kamiar Mohaddes and M. Hashem Pesarann, July 2016
 Tests of Policy Ineffectiveness in Macroeconometrics, by M. Hashem Pesaran and Ron P. Smith, CAFE Research Paper No. 14.07, June 2014, revised January 2015
 To Pool or not to Pool: Revisited, by M. Hashem Pesaran and Qiankun Zhou, June 2015
 A multicountry approach to forecasting output growth using PMIs, by Alexander Chudik, Valerie Grossmanz and M. Hashem Pesaran, forthcoming in the Journal of Econometrics, January 2016.
 Is There a Debtthreshold Effect on Output Growth?, by Alexander Chudik, Kamiar Mohaddes, M. Hashem Pesaran, and Mehdi Raissi, forthcoming in the Review of Economics and Statistics, November 2015.
 Exponent of Crosssectional Dependence: Estimation and Inference, by Natalia Bailey, George Kapetanios and M. Hashem Pesaran, forthcoming in the Journal of Applied Econometrics, January 2015.
 A Two Stage Approach to SpatioTemporal Analysis with Strong and Weak CrossSectional Dependence, by Natalia Bailey, Sean Holly and M. Hashem Pesaran, CESifo Working Paper No. 4592, forthcoming in the Journal of Applied Econometrics, January 2015.
 Econometric Analysis of Production Networks with Dominant Units, by M. Hashem Pesarann and Cynthia Fan Yang, USC Dornsife Working Paper No. 1625, October 2016
 An Exponential Class of Dynamic Binary Choice Panel Data Models with Fixed Effects, by Majid M. AlSadoon, Tong Li and M. Hashem Pesaran,CESifo Working Paper No. 4033, forthcoming in Econometrics Reviews, August 2016.
 Doublequestion Survey Measures for the Analysis of Financial Bubbles and Crashes, by M. Hashem Pesarann and Ida Johnsson, December 2016, revised May 2017
 Oil Prices and the Global Economy: Is It Different This Time Around?, by Kamiar Mohaddes and M. Hashem Pesaran, July 2016
 Doublequestion Survey Measures for the Analysis of Financial Bubbles and Crashes, by M. Hashem Pesaran and Ida Johnsson, December 2016, revised January 2017
 Doublequestion Survey Measures for the Analysis of Financial Bubbles and Crashes, by M. Hashem Pesaran and Ida Johnsson, December 2016
 Big Data Analytics: A New Perspective, by Alexander Chudik, George Kapetanios and M. Hashem Pesaran, February 2016
 CountrySpecific Oil Supply Shocks and the Global Economy: A Counterfactual Analysis, by Kamiar Mohaddes and M. Hashem Pesaran, forthcoming in Energy Economics, July 2016.
 CountrySpecific Oil Supply Shocks and the Global Economy: A Counterfactual Analysis, by Kamiar Mohaddes and M. Hashem Pesaran, May 2015
 A Multiple Testing Approach to the Regularisation of Large Sample Correlation Matrices, by Natalia Bailey, M. Hashem Pesaran and L. Vanessa Smith, CAFE Research Paper No. 14.05, May 2014, revised November 2015
 An Exponential Class of Dynamic Binary Choice Panel Data Models with Fixed Effects, by Majid M. AlSadoon, Tong Li and M. Hashem Pesaran,CESifo Working Paper No. 4033, October 2012, revised January 2016
 Estimation of Timeinvariant Effects in Static Panel Data Models, by M. Hashem Pesaran and Qiankun Zhou, September 2014
 LongRun Effects in Large Heterogenous Panel Data Models with CrossSectionally Correlated Errors, by Alexander Chudik, Kamiar Mohaddes, M. Hashem Pesaran and Mehdi Raissi, forthcoming in Advances in Econometrics, V36 Essays in Honor of Aman Ullah, 2016.
 Theory and Practice of GVAR Modeling, by Alexander Chudik, and M. Hashem Pesaran, SSRN Research Paper Series No. 14.04, forthcoming in the Journal of Economic Surveys, September 2014.
 Business Cycle Effects of Credit and Technology Shocks in a DSGE Model with Firm Default, by M. Hashem Pesaran and TengTeng Xu, CWPE Working paper. No. 1159, CESifo Working Paper No. 3609, IZA Discussion Paper No. 6027, October 2011, under revision
 An Exponential Class of Dynamic Binary Choice Panel Data Models with Fixed Effects", by Majid M. AlSadoon, Tong Li and M. Hashem Pesaran, CESifo Working Paper No. 4033, October 2012, revised August 2014
 Robust Standard Errors in Transformed Likelihood Estimation of Dynamic Panel Data Models with CrossSectional Heteroskedasticity, by Kazuhiko Hayakawa and M. Hashem Pesaran, CWPE Working Paper No. 1224, IZA Discussion Paper 6583, CESifo Working Paper No.3850, forthcoming in the Journal of Econometrics, March 2015.
 Common Correlated Effects Estimation of Heterogeneous Dynamic Panel Data Models with Weakly Exogenous Regressors, by Alexander Chudik, and M. Hashem Pesaran, CESifo Working Paper No. 4232 and CAFE Research Paper No. 13.14, IZA Discussion Paper No. 6618, forthcoming in the Journal of Econometrics July 2014.
 Testing Weak CrossSectional Dependence in Large Panels, by M. Hashem Pesaran, CWPE Working Paper No. 1208, IZA Discussion Paper No. 6432, forthcoming in Econometric Reviews, January 2012.
 Debt, Inflation and Growth: Robust Estimation of LongRun Effects in Dynamic Panel Data Models, by Alexander Chudik, Kamiar Mohaddes, M. Hashem Pesaran, and Mehdi Raissi, November 2013
 A multicountry approach to forecasting output growth using PMIs, by Alexander Chudik, Valerie Grossmanz and M. Hashem Pesaran, November 2014
 Is There a Debtthreshold Effect on Output Growth?, by Alexander Chudik, Kamiar Mohaddes, M. Hashem Pesaran, and Mehdi Raissi, July 2015
 A Multiple Testing Approach to the Regularisation of Large Sample Correlation Matrices, by Natalia Bailey, M. Hashem Pesaran and L. Vanessa Smith, CAFE Research Paper No. 14.05, May 2014, revised January 2015
 LongRun Effects in Large Heterogenous Panel Data Models with CrossSectionally Correlated Errors, by Alexander Chudik, Kamiar Mohaddes, M. Hashem Pesaran and Mehdi Raissi, January 2015
 Robust Standard Errors in Transformed Likelihood Estimation of Dynamic Panel Data Models with CrossSectional Heteroskedasticity, by Kazuhiko Hayakawa and M. Hashem Pesaran, CWPE Working Paper No. 1224, IZA Discussion Paper 6583, CESifo Working Paper No.3850, April 2012, revised January 2014
 Exponent of Crosssectional Dependence: Estimation and Inference, by Natalia Bailey, George Kapetanios and M. Hashem Pesaran, November 2013, revised December 2014
 A Multiple Testing Approach to the Regularisation of Large Sample Correlation Matrices, by Natalia Bailey, M. Hashem Pesaran and L. Vanessa Smith, CAFE Research Paper No. 14.05, May 2014
 Constructing Multicountry Rational Expectations Models, by Stephane Dees, M. Hashem Pesaran, Ron P. Smith and L. Vanessa Smith, CESifo Working Papers No. 3081, October 2012, forthcoming in Oxford Bulletin of Economics and Statistics
 Large Panel Data Models with CrossSectional Dependence: A Survey, by Alexander Chudik, and M. Hashem Pesaran, CESifo Working Paper No. 4371, August 2013, forthcoming in B. H. Baltagi (Ed.), The Oxford Handbook on Panel Data. Oxford University Press.
 Tests of Policy Ineffectiveness in Macroeconometrics, by M. Hashem Pesaran and Ron P. Smith, CAFE Research Paper No. 14.07, June 2014
 A Two Stage Approach to Spatiotemporal Analysis with Strong and Weak CrossSectional Dependence", by Natalia Bailey, Sean Holly and M. Hashem Pesaran, December 2013, revised July 2014
 Exponent of Crosssectional Dependence: Estimation and Inference, by Natalia Bailey, George Kapetanios and M. Hashem Pesaran, November 2013
 Theory and Practice of GVAR Modeling, by Alexander Chudik, and M. Hashem Pesaran, SSRN Research Paper Series No. 14.04, May 2014
 An Exponential Class of Dynamic Binary Choice Panel Data Models with Fixed Effects, by Majid M. AlSadoon, Tong Li and M. Hashem Pesaran,CESifo Working Paper No. 4033, October 2012, revised December 2012
 A Two Stage Approach to Spatiotemporal Analysis with Strong and Weak CrossSectional Dependence", by Natalia Bailey, Sean Holly and M. Hashem Pesaran, December 2013
 Common Correlated Effects Estimation of Heterogeneous Dynamic Panel Data Models with Weakly Exogenous Regressors, Alexander Chudik, and M. Hashem Pesaran, CESifo WP Number 4232, May 2013
 Counterfactual Analysis in Macroeconometrics: An Empirical Investigation into the Effects of Quantitative Easing, by M. Hashem Pesaran and Ron P Smith, IZA Discussion Paper No. 6618, May 2012, revised June 2012
 Optimal Forecasts in the Presence of Structural Breaks, by M. Hashem Pesaran, Andreas Pick and Mikhail Pranovich, (2013), forthcoming in Journal of Econometrics
 Signs of Impact Effects in Time Series Regression Models, by M. Hashem Pesaran and Ron P Smith, CESifo Working Paper, CAFE Research Paper No. 13.22, (2013), forthcoming in Economics Letters
 One Hundred Years of Oil Income and the Iranian Economy: A Curse or a Blessing?, by Kamiar Mohaddes, and M. Hashem Pesaran, CESifo Working Paper Series No. 4118, February 2013, forthcoming in Parvin Alizadeh and Hassan Hakimian (eds.), Iran and the Global Economy: Petro Populism, Islam and Economic Sanctions. Routledge, London.
 Panel Unit Root Test in the Presence of a Multifactor Error Structure", M. Hashem Pesaran, L. V. Smith, and T. Yamagata, December 2007. CWPE No. 0775, CESifo Working Papers, No. 2193, January 2008, IZA Discussion Paper No. 3254, December 2007. The University of York, Discussion Papers in Economics 08/03. Revised November 2012, forthcoming in Journal of Econometrics
 Testing CAPM with a Large Number of Assets, by M. Hashem Pesarann and Takashi Yamagata, February 2012
 An Empirical Growth Model for Major Oil Exporters, by Hadi Salehi Esfahani, Kamiar Mohaddes and M. Hashem Pesaran, (2012), forthcoming in Journal of Applied Econometrics
 Aggregation in Large Dynamic Panels, by M. Hashem Pesaran, Alexander Chudik, (2012), forthcoming in Journal of Econometrics
 Robust Standard Errors in Transformed Likelihood Estimation of Dynamic Panel Data Models, by Kazuhiko Hayakawa and M. Hashem Pesaran, CWPE Working Paper No. 1224, IZA Discussion Paper 6583, Cesifo Working Paper No.3850, April 2012, revised April 2012
 Signs of Impact Effects in Time Series Regression Models, by M. Hashem Pesaran and Ron P Smith, CESifo Working Paper, CAFE Research Paper No. 13.22 , October 2013
 Large Panel Data Models with CrossSectional Dependence: A Survey, by Alexander Chudik, and M. Hashem Pesaran, CESifo Working Paper No. 4371, August 2013
 One Hundred Years of Oil Income and the Iranian Economy: A Curse or a Blessing?, by Kamiar Mohaddes, and M. Hashem Pesaran, CESifo Working Paper Series No. 4118, December 2012, revised February 2013.
 Supply, Demand and Monetary Policy Shocks in a MultiCountry New Keynesian Model, by Stephane Dees, M. Hashem Pesaran, Ron P. Smith and L. Vanessa Smith, CESifo Working Papers No. 3081, June 2011, revised October 2012
 Counterfactual Analysis in Macroeconometrics: An Empirical Investigation into the Effects of Quantitative Easin, by M. Hashem Pesaran and Ron P Smith, May 2012
 One Hundred Years of Oil Income and the Iranian Economy: A Curse or a Blessing?, by Kamiar Mohaddes, and M. Hashem Pesaran, December 2012
 Testing Weak CrossSectional Dependence in Large Panels, by M. Hashem Pesaran, January 2012, Revised January 2013
 Econometric Analysis of High Dimensional VARs Featuring a Dominant Unit, by M. Hashem Pesaran and Alexander Chudik, (2011), forthcoming in the Econometrics Review.
 Common Correlated Effects Estimation of Heterogeneous Dynamic Panel Data Models with Weakly Exogenous Regressors, by Alexander Chudik, and M. Hashem Pesaran, April 2013
 Panel Unit Root Test in the Presence of a Multifactor Error Structure, by M. Hashem Pesaran, L. Vanessa. Smith, and Takashi Yamagata, (2013), Forthcoming in Journal of Econometrics, Revised 2012
 A Panel Unit Root Test in the Presence of a Multifactor Error Structure, by M. Hashem Pesaran, L. Vanessa. Smith, and Takashi Yamagata December, 2007, Revised September 2009
 Business Cycle Effects of Credit and Technology Shocks in a DSGE Model with Firm Default, by M. Hashem Pesaran and TengTeng Xu, October 2011
 Optimal Forecasts in the Presence of Structural Breaks, by M. Hashem Pesaran, Andreas Pick and Mikhail Pranovich, October 2011, Revised December 2011
 On Identification of Bayesian DSGE Models, by Gary Koop, M. Hashem Pesaran and Ron P. Smith, March 2011, Revised August 2012
 Testing Weak CrossSectional Dependence in Large Panels, by M. Hashem Pesaran, January 2012
 On Identification of Bayesian DSGE Models, by Gary Koop, M. Hashem Pesaran and Ron P. Smith, March 2011, Revised September 2011
 Oil Exports and the Iranian Economy, by Hadi Salehi Esfahani, Kamiar Mohaddes and M. Hashem Pesaran, April 2012
 Oil Exports and the Iranian Economy, by Hadi Salehi Esfahani, Kamiar Mohaddes, and M. Hashem Pesaran, October, 2009
 On the Interpretation of Panel Unit Root Tests, by M. Hashem Pesaran, September 2011
 Aggregation in Large Dynamic Panels, by M. Hashem Pesaran, Alexander Chudik, January 2011, Revised November 2011
 Beyond the DSGE Straitjacket, by M. Hashem Pesaran and Ron P. Smith, May 2011
 China's Emergence in the World Economy and Business Cycles in Latin America, by Ambrogio CesaBianchi, M. Hashem Pesaran, Alessandro Rebucci and TengTeng Xu, July 2011
 Beyond the DSGE straitjacket, by M. Hashem Pesaran and Ron P. Smith, April 2011
 Econometric Analysis of High Dimensional VARs Featuring a Dominant Unit, by M. Hashem Pesaran and Alexander Chudik, March, 2010
 Supply, Demand and Monetary Policy Shocks in a MultiCountry New Keynesian Model, by Stephane Dees, M. Hashem Pesaran, L. Vanessa Smith and Ron P. Smith, May 2010
 Diagnostic Tests of Cross Section Independence for Nonlinear Panel Data Models, by Cheng Hsiao, M. Hashem Pesaran and Andreas Pick April, 2007, Revised July 2010
 Lumpy Price Adjustments: A Microeconometric Analysis, Emmanuel Dhyney, Catherine Fuss, M. Hashem Pesaran, Patrick Sevestre April, 2007, Revised August 2008
 Large Panels with Common Factors and Spatial Correlation, M. Hashem Pesaran and Elisa Tosetti August, 2007, Revised May 2010
 Variable Selection, Estimation and Inference for Multiperiod Forecasting Problems, by M. Hashem Pesaran, A. Pick and A. Timmerman April, 2010
 Panels with Nonstationary Multifactor Error Structures , by G. Kapetanios, M. Hashem Pesaran and T. Yamagata July, 2006, Revised June 2009
 Spatial and Temporal Diffusion of House Prices in the UK, by Sean Holly, M. Hashem Pesaran and Takashi Yamagata December, 2009
 Predictability of Asset Returns and the Efficient Market Hypothesis, by M. Hashem Pesaran May 2010
 Weak and Strong Cross Section Dependence and Estimation of Large Panels, by Alexander Chudik, M. Hashem Pesaran and Elisa Tosetti, April, 2010
 Infinite Dimensional VARs and Factor Models, Alexander Chudik and M. Hashem Pesaran November, 2007, revised January 2010
 Forecasting Random Walks Under Drift Instability, by M. Hashem Pesaran and Andreas Pick, March, 2008, Revised January 2009
 A VECX* Model of the Swiss Economy, by Katrin AssenmacherWesche and M. Hashem Pesaran February, 2008
 Modelling Volatilities and Conditional Correlations in Futures Markets with a Multivariate t Distribution, Bahram Pesaran and M. Hashem Pesaran June, 2007

"A OneCovariate at a Time, Multiple Testing Approach to Variable Selection in HighDimensional Linear Regression Models", by Alexander Chudik, George Kapetanios and M. Hashem Pesaran, February 2016, revised November 2016
Abstract: Model specification and selection are recurring themes in econometric analysis. Both topics become considerably more complicated in the case of largedimensional data sets where the set of specification possibilities can become quite large. In the context of linear regression models, penalised regression has become the de facto benchmark technique used to trade off parsimony and fit when the number of possible covariates is large, often much larger than the number of available observations. However, issues such as the choice of a penalty function and tuning parameters associated with the use of penalized regressions remain contentious. In this paper, we provide an alternative approach that considers the statistical significance of the individual covariates one at a time, whilst taking full account of the multiple testing nature of the inferential problem involved. We refer to the proposed method as One Covariate at a Time Multiple Testing (OCMT) procedure. The OCMT provides an alternative to penalised regression methods: It is based on statistical inference and is therefore easier to interpret and relate to the classical statistical analysis, it allows working under more general assumptions, it is faster, and performs well in small samples for almost all of the different sets of experiments considered in this paper. We provide extensive theoretical and Monte Carlo results in support of adding the proposed OCMT model selection procedure to the toolbox of applied researchers. The usefulness of OCMT is also illustrated by an empirical application to forecasting U.S. output growth and inflation.
JEL Classifications: C52, C55
Key Words: One covariate at a time, multiple testing, model selection, high dimensionality, penalised regressions, boosting, Monte Carlo experiments.
Full Text: http://www.econ.cam.ac.uk/peoplefiles/emeritus/mhp1/wp16/ChudikKapetaniosPesaran_14Nov2016.pdf
Supplement 1: http://www.econ.cam.ac.uk/peoplefiles/emeritus/mhp1/wp16/Supplement_Theory_ChudikKapetaniosPesaran_10Nov2016.pdf
Supplement 2: http://www.econ.cam.ac.uk/peoplefiles/emeritus/mhp1/wp16/Supplement_MC_ChudikKapetaniosPesaran_10Nov2016.pdf

"To Pool or not to Pool: Revisited", by M. Hashem Pesaran and Qiankun Zhou, forthcoming in Oxford Bulletin of Economics and Statistics, October 2017.
Abstract: This paper provides a new comparative analysis of pooled least squares and fixed effects estimators of the slope coefficients in the case of panel data models when the time dimension (T) is xed while the cross section dimension (N) is allowed to increase without bounds. The individual effects are allowed to be correlated with the regressors, and the comparison is carried out in terms of an exponent coefficients, δ, which measures the degree of pervasiveness of the fixed effects in the panel. The use of δ allows us to distinguish between poolability of small N dimensional panels with large T from large N dimensional panels with small T. It is shown that the pooled estimator remains consistent so long as δ < 1, and is asymptotically normally distributed if δ < 1/2, for a fixed T and as N → ∞. It is further shown that when δ < 1/2, the pooled estimator is more efficient than the fixed effects estimator. We also propose a Hausman type diagnostic test of δ < 1/2 as a simple test of poolability, and propose a pretest estimator that could be used in practice. Monte Carlo evidence supports the main theoretical findings and gives some indications of gains to be made from pooling when δ < 1/2.
JEL Classifications: C01, C23, C33
Key Words: Short panel, Fixed effects estimator, Pooled estimator, Efficiency.
Full Text: http://www.econ.cam.ac.uk/peoplefiles/emeritus/mhp1/fp17/PesaranZhouTopoolornottopoolOct2017.pdf

"Testing for Alpha in Linear Factor Pricing Models with a Large Number of Securities", by M. Hashem Pesaran and Takashi Yamagata, March 2017
Abstract: This paper proposes a novel test of zero pricing errors for the linear factor pricing model when the number of securities, N, can be large relative to the time dimension, T, of the return series. The test is based on Student t tests of individual securities and has a number of advantages over the existing standardised Wald type tests. It allows for nonGaussianity and general forms of weakly cross correlated errors. It does not require estimation of an invertible error covariance matrix, it is much faster to implement, and is valid even if N is much larger than T. Monte Carlo evidence shows that the proposed test performs remarkably well even when T = 60 and N = 5, 000. The test is applied to monthly returns on securities in the S&P 500 at the end of each month in real time, using rolling windows of size 60. Statistically significant evidence against SharpeLintner CAPM and FamaFrench three factor models are found mainly during the recent financial crisis. Also we find a significant negative correlation between a twelvemonths moving average pvalues of the test and excess returns of long/short equity strategies (relative to the return on S&P 500) over the period November 1994 to June 2015, suggesting that abnormal profits are earned during episodes of market inefficiencies.
JEL Classifications: C12, C15, C23, G11, G12
Key Words: CAPM, Testing for alpha, Weak and spatial error crosssectional dependence, S&P 500 securities, Long/short equity strategy.
Full Text: http://www.econ.cam.ac.uk/peoplefiles/emeritus/mhp1/wp17/PY_LFPM_11_March_2017_Paper.pdf
Supplement: http://www.econ.cam.ac.uk/peoplefiles/emeritus/mhp1/wp17/PY_LFPM_11_March_2017_Supplement.pdf

"HalfPanel Jackknife Fixed Effects Estimation of Panels with Weakly Exogenous Regressors", by Alexander Chudik, M. Hashem Pesarann and JuiChung Yang, SSRN Working Paper No. 281, September 2016
Abstract: This paper considers estimation and inference in fixed effects (FE) linear panel regression models with lagged dependent variables and/or other weakly exogenous (or predetermined) regressors when N (the cross section dimension) is large relative to T (the time series dimension). The paper first derives a general formula for the bias of the FE estimator which is a generalization of the Nickell type bias derived in the literature for the pure dynamic panel data models. It shows that in the presence of weakly exogenous regressors, inference based on the FE estimator will result in size distortions unless N/T is suffciently small. To deal with the bias and size distortion of FE estimator when N is large relative to T, the use of halfpanel Jackknife FE estimator is proposed and its asymptotic distribution is derived. It is shown that the bias of the proposed estimator is of order [code], and for valid inference it is only required that N/T[code], as N, T [code] jointly. Extensions to panel data models with time effects (TE), for balanced as well as unbalanced panels, are also provided. The theoretical results are illustrated with Monte Carlo evidence. It is shown that the FE estimator can suffer from large size distortions when N > T, with the proposed estimator showing little size distortions. The use of halfpanel jackknife FETE estimator is illustrated with two empirical applications from the literature.
JEL Classifications: C32, E17, E32, F44, F47, O51, Q43.
Key Words: Panel Data Models, Weakly Exogenous Regressors, Lagged Dependent Variable, Fixed Effects, Time Effects, Unbalanced Panels, HalfPanel Jackknife, Bias Correction
Full Text: http://www.econ.cam.ac.uk/peoplefiles/emeritus/mhp1/wp16/CPY_jackknifeFE_13Sep2016.pdf
Supplement: http://www.econ.cam.ac.uk/peoplefiles/emeritus/mhp1/wp16/CPY_jackknifeFE_supplement_12Sep2016.pdf
Data: http://www.econ.cam.ac.uk/peoplefiles/emeritus/mhp1/wp16/MatlabCodesandDataforChudikPesaranandYang(2016).rar

"Counterfactual Analysis in Macroeconometrics: An Empirical Investigation into the Effects of Quantitative Easing", by M. Hashem Pesaran and Ron P Smith, IZA Discussion Paper No. 6618, May 2012, revised June 2014
Abstract: The policy innovations that followed the recent Great Recession, such as unconventional monetary policies, prompted renewed interest in the question of how to measure the effectiveness of such policy interventions. To test policy effectiveness requires a model to construct a counterfactual for the outcome variable in the absence of the policy intervention and a way to determine whether the differences between the realised outcome and the modelbased counter factual outcomes are larger than what could have occurred by chance in the absence of policy intervention. Pesaran & Smith (2014b) propose tests of policy ineffectiveness in the context of macroeconometric rational expectations dynamic stochastic general equilibrium models. When we are certain of the specification, estimation of the complete system imposing all the crossequation restrictions implied by the full structural model is more efficient. But if the full model is misspecified, one may obtain more reliable estimates of the counterfactul outcomes from a parsimonious reduced form policy response equation, which conditions on lagged values, and on the policy measures and variables known to be invariant to the policy intervention. We propose policy ineffectiveness tests based on such reduced forms and illustrate the tests with an application to the unconventional monetary policy known as quantitative easing (QE) adopted in the UK.
JEL Classifications: C18, C54, E65
Key Words: Counterfactuals, policy analysis, policy ineffectiveness test, macroeconomics, quantitative easing (QE)
Full Text: http://www.econ.cam.ac.uk/peoplefiles/emeritus/mhp1/wp14/PSonCF_17June2014.pdf

"Oil Prices and the Global Economy: Is It Different This Time Around?", by Kamiar Mohaddes and M. Hashem Pesarann, July 2016
Abstract: The recent plunge in oil prices has brought into question the generally accepted view that lower oil prices are good for the US and the global economy. In this paper, using a quarterly multicountry econometric model, we first show that a fall in oil prices tends relatively quickly to lower interest rates and inflation in most countries, and increase global real equity prices. The effects on real output are positive, although they take longer to materialize (around 4 quarters after the shock). We then reexamine the effects of low oil prices on the US economy over different subperiods using monthly observations on real oil prices, real equity prices and real dividends. We confirm the perverse positive relationship between oil and equity prices over the period since the 2008 financial crisis highlighted in the recent literature, but show that this relationship has been unstable when considered over the longer time period of 19462016. In contrast, we find a stable negative relationship between oil prices and real dividends which we argue is a better proxy for economic activity (as compared to equity prices). On the supply side, the effects of lower oil prices differ widely across the different oil producers, and could be perverse initially, as some of the major oil producers try to compensate their loss of revenues by raising production. Taking demand and supply adjustments to oil price changes as a whole, we conclude that oil markets equilibrate but rather slowly, with large episodic swings between low and high oil prices.
JEL Classifications: C32, E17, E32, F44, F47, O51, Q43.
Key Words: Oil prices, equity prices, dividends, economic growth, oil supply, global oil markets, and international business cycle.
Full Text: http://www.econ.cam.ac.uk/peoplefiles/emeritus/mhp1/wp16/MP_Oil_Prices_&_Global_Economy_160703.pdf

"Tests of Policy Ineffectiveness in Macroeconometrics", by M. Hashem Pesaran and Ron P. Smith, CAFE Research Paper No. 14.07, June 2014, revised January 2015
Abstract: This paper considers tests of the null hypothesis of the ineffectiveness of a policy intervention, defined as a change in the parameters of a policy rule, in the context of a macroeconometric dynamic stochastic general equilibrium (DSGE) model. This is an ex post evaluation of an intervention in a single country, where data are available before and after the interven tion. The tests are based on the difference between the realisations of the outcome variable of interest and counterfactuals based on no policy intervention, using only the preintervention parameter estimates, and in consequence the Lucas Critique does not apply. We show that such tests will have power to detect the effect of a policy intervention on a target outcome variable that changes the steady state value of that variable, e.g. the target inflation rate. They will have less power against interventions which do not change the steady state, since these typically only have transitory effects. Asymptotic distributions of the proposed tests are derived both when the post intervention sample is fixed as the preintervention sample expands, and when both samples rise jointly but at different rates. The performance of the test is illustrated by a simulated policy analysis of a three equation New Keynesian Model.
JEL Classifications: C18, C54, E65.
Key Words: Counterfactuals, policy analysis, policy ineffectiveness test, macroeconomics.
Full Text: http://www.econ.cam.ac.uk/peoplefiles/emeritus/mhp1/wp15/PSonPI_16January2015.pdf

"To Pool or not to Pool: Revisited", by M. Hashem Pesaran and Qiankun Zhou, June 2015
Abstract: This paper provides a new comparative analysis of pooled least squares and fixed effects estimators of the slope coefficients in the case of panel data models when the time dimension (T) is fixed while the cross section dimension (N) is allowed to increase without bounds. The individual effects are allowed to be correlated with the regressors, and the comparison is carried out in terms of an exponent coefficient, δ, which measures the degree of pervasiveness of the fixed effects in the panel. It is shown that the pooled estimator remains consistent so long as δ < 1, and is asymptotically normally distributed if δ < 1/2, for a fixed T and as N → ∞. It is further shown that when δ < 1/2, the pooled estimator is more efficient than the fixed effects estimator. Monte Carlo evidence provided supports the main theoretical findings and gives some indications of gains to be made from pooling when δ < 1/2. The problem of how to estimate δ in short T panels is not considered in this paper.
JEL Classifications: C01, C23, C33
Key Words: Short panel, Fixed effects estimator, Pooled estimator, Efficiency.
Full Text: http://www.econ.cam.ac.uk/peoplefiles/emeritus/mhp1/wp15/Pesaran&ZhouTopoolornottopool_revisited_June152015.pdf

"A Two Stage Approach to SpatioTemporal Analysis with Strong and Weak CrossSectional Dependence", by Natalia Bailey, Sean Holly, and M. HashemPesaran, CESifo Working Paper No. 4592, forthcoming in the Journal of Applied Econometrics, January 2015.
Abstract: An understanding of the spatial dimension of economic and social activity requires methods that can separate out the relationship between spatial units that is due to the effect of common factors from that which is purely spatial even in an abstract sense. The same applies to the empirical analysis of networks in general. We use cross unit averages to extract common factors (viewed as a source of strong crosssectional dependence) and compare the results with the principal components approach widely used in the literature. We then apply multiple testing procedures to the defactored observations in order to determine significant bilateral correlations (signifying connections) between spatial units and compare this to an approach that just uses distance to determine units that are neighbours. We apply these methods to real house price changes at the level of Metropolitan Statistical Areas in the USA, and estimate a heterogeneous spatiotemporal model for the defactored real house price changes and obtain significant evidence of spatial connections, both positive and negative.
JEL Classifications: C21, C23
Key Words: Spatial and factor dependence, spatiotemporal models, positive and negative connections, house price changes.
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/fp14/bhp_Dec_16_2014_JAE.pdf

"A multicountry approach to forecasting output growth using PMIs", by Alexander Chudik, Valerie Grossmanz and M. Hashem Pesaran, forthcoming in the Journal of Econometrics, January 2016.
Abstract: This paper derives new theoretical results for forecasting with Global VAR (GVAR) models. It is shown that the presence of a strong unobserved common factor can lead to an undetermined GVAR model. To solve this problem, we propose augmenting the GVAR with additional proxy equations for the strong factors and establish conditions under which forecasts from the augmented GVAR model (AugGVAR) uniformly converge in probability (as the panel dimensions N,T [code] ∞ such that N/T → k for some 0 < k < ∞) to the infeasible optimal forecasts obtained from a factoraugmented highdimensional VAR model. The small sample properties of the proposed solution are investigated by Monte Carlo experiments as well as empirically. In the empirical part, we investigate the value of the information content of Purchasing Managers Indices (PMIs) for forecasting global (48 countries) growth, and compare forecasts from Aug GVAR models with a number of datarich forecasting methods, including Lasso, Ridge, partial least squares and factorbased methods. It is found that (a) regardless of the forecasting meth ods considered, PMIs are useful for nowcasting, but their value added diminishes quite rapidly with the forecast horizon, and (b) AugGVAR forecasts do as well as other datarich forecasting techniques for short horizons, and tend to do better for longer forecast horizons.
JEL Classifications: C53, E37.
Key Words: Global VARs, Highdimensional VARs, Augmented GVAR, Forecasting, Nowcasting, Datarich methods, GDP and PMIs
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/fp16/CGP_GDPnowcasting_10November2014.pdf

"Exponent of Crosssectional Dependence: Estimation and Inference", by Natalia Bailey, George Kapetanios and M. Hashem Pesaran, forthcoming in the Journal of Applied Econometrics, January 2015.
Abstract: In this paper, we provide a characterisation of the degree of crosssectional dependence in a two dimensional array, [code] in terms of the rate at which the variance of the crosssectional average of the observed data varies with N. We show that under certain conditions this is equivalent to the rate at which the largest eigenvalue of the covariance matrix of [code] rises with N. We represent the degree of crosssectional dependence by , defined by the standard deviation, [code], where [code] is a simple crosssectional average of [code]. We refer to as the `exponent of crosssectional dependence', and show how it can be consistently estimated for values of > 1/2. We propose bias corrected estimators, derive their asymptotic properties and consider a number of extensions. We include a detailed Monte Carlo simulation study supporting the theoretical results. We also provide a number of empirical applications investigating the degree of interlinkages of real and financial variables in the global economy, the extent to which macroeconomic variables are interconnected across and within countries, and present recursive estimates of applied to excess returns on securities included in the Standard & Poor 500 index.
JEL Classifications: C21, C32
Key Words: Cross correlations, Crosssectional dependence, Crosssectional averages, Weak and strong factor models
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/fp15/BKP_26_Jan_2015.pdf
Supplementary Appendices: http://www.econ.cam.ac.uk/emeritus/mhp1/fp15/BKP_exponent_supplement_26_Jan_2015.pdf
Codes and Data: http://www.econ.cam.ac.uk/emeritus/mhp1/fp15/BKP_GAUSS_procedures.zip

"Is There a Debtthreshold Effect on Output Growth?", by Alexander Chudik, Kamiar Mohaddes, M. Hashem Pesaran, and Mehdi Raissi, forthcoming in the Review of Economics and Statistics, November 2015. Abstract: This paper studies the longrun impact of public debt expansion on economic growth and investigates whether the debtgrowth relation varies with the level of indebtedness. Our contribution is both theoretical and empirical. On the theoretical side, we develop tests for threshold effects in the context of dynamic heterogeneous panel data models with crosssectionally dependent errors and illustrate, by means of Monte Carlo experiments, that they perform well in small samples. On the empirical side, using data on a sample of 40 countries (grouped into advanced and developing) over the 19652010 period, we find no evidence for a universally applicable threshold effect in the relationship between public debt and economic growth, once we account for the impact of global factors and their spillover effects. Regardless of the threshold, however, we find significant negative longrun effects of public debt buildup on output growth. Provided that public debt is on a downward trajectory, a country with a high level of debt can grow just as fast as its peers.
JEL Classifications: C23, E62, F34, H6
Key Words: Panel tests of threshold effects, longrun relationships, estimation and inference, large dynamic heterogeneous panels, crosssection dependence, debt, and inflation.
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/fp16/CMPR_July32015_2(uploadedREStat).pdf
Supplement: http://www.econ.cam.ac.uk/emeritus/mhp1/fp16/Supplement_03July2015_3(uploadREStat).pdf
Matlab Codes for the CSDL Estimators: http://www.econ.cam.ac.uk/peoplefiles/cto/km418/CMPR_CSDL.zip
Matlab Codes for Panel Tests of Threshold Effects: http://www.econ.cam.ac.uk/peoplefiles/cto/km418/CMPR_Threshold_Codes.zip

"Econometric Analysis of Production Networks with Dominant Units", by M. Hashem Pesarann and Cynthia Fan Yang, USC Dornsife Working Paper No. 1625, October 2016
Abstract: This paper builds on the work of Acemoglu et al. (2012) and considers a production network with unobserved common technological factor and establishes general conditions under which the network structure contributes to aggregate fluctuations. It introduces the notions of strongly and weakly dominant units, and shows that at most a finite number of units in the network can be strongly dominant, while the number of weakly dominant units can rise with N (the cross section dimension). This paper further establishes the equivalence between the highest degree of dominance in a network and the inverse of the shape parameter of the power law. A new extremum estimator for the degree of pervasiveness of individual units in the network is proposed, and is shown to be robust to the choice of the underlying distribution. Using Monte Carlo techniques, the proposed estimator is shown to have satisfactory small sample properties. Empirical applications to US inputoutput tables suggest the presence of production sectors with a high degree of pervasiveness, but their effects are not sufficiently pervasive to be considered as strongly dominant.
JEL Classifications: C12, C13, C23, C67, E32.
Key Words: Aggregate fluctuations, strongly and weakly dominant units, spatial models, outdegrees, degree of pervasiveness, power law, inputoutput tables, US economy
Full Text: http://www.econ.cam.ac.uk/peoplefiles/emeritus/mhp1/wp16/Pesaran_and_Yang_analysis_of_networks_October_2016_SSRNid2851148.pdf

"An Exponential Class of Dynamic Binary Choice Panel Data Models with Fixed Effects", by Majid M. AlSadoon, Tong Li and M. Hashem Pesaran, CESifo Working Paper No. 4033, forthcoming in Econometrics Reviews, August 2016.
Abstract: This paper proposes an exponential class of dynamic binary choice panel data models for the analysis of short T (time dimension) large N (cross section dimension) panel data sets that allows for unobserved heterogeneity (fixed effects) to be arbitrarily correlated with the covariates. The paper derives moment conditions that are in variant to the fixed effects which are then used to identify and estimate the parameters of the model. Accordingly, GMM estimators are proposed that are consistent and asymptotically normally distributed at the rootN rate. We also study the conditional likelihood approach, and show that under exponential specification it can identify the effect of state dependence but not the effects of other covariates. Monte Carlo experiments show satisfactory nite sample performance for the proposed estimators, and investigate their robustness to missspecification.
JEL Classifications: C23, C25
Key Words: Dynamic Discrete Choice, Fixed Effects, Panel Data, GMM, CMLE.
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/fp16/AlSadoonLiandPesaranDBC28August2016.pdf
Supplement: http://www.econ.cam.ac.uk/emeritus/mhp1/fp16/SupplementtoAlSadoonLiandPesaranDBCAPE_probitMCexperimentsr.pdf

"Doublequestion Survey Measures for the Analysis of Financial Bubbles and Crashes", by M. Hashem Pesarann and Ida Johnsson, December 2016, revised May 2017
Abstract: This paper proposes a new doublequestion survey whereby an individual is presented with two sets of questions; one on beliefs about current asset values and another on price expectations. A theoretical asset pricing model with heterogeneous agents is advanced and the existence of a negative relationship between price expectations and asset valuations is established, which is tested using survey results on equity, gold and house prices. Leading indicators of bubbles and crashes are proposed and their potential value is illustrated in the context of a dynamic panel regression of realized house price changes across a number of key MSAs in the US.
JEL Classifications: C83, D84, G12, G14.
Key Words: Price expectations, bubbles and crashes, house prices, belief valuations.
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/wp17/PJDoubleQuestionSurveyPaper28May2017(mainpaper).pdf
Suppliment: http://www.econ.cam.ac.uk/emeritus/mhp1/wp17/PJDoubleQuestionSurveyPaper28May2017(Supplement).pdf
Data: http://www.econ.cam.ac.uk/peoplefiles/emeritus/mhp1/wp17/Double_Q_survey_data_Aug_2012Jan_2013.zip
Replication: http://www.econ.cam.ac.uk/peoplefiles/emeritus/mhp1/wp17/Double_Q_Survey_Replication.zip

"Oil Prices and the Global Economy: Is It Different This Time Around?", by Kamiar Mohaddes and M. Hashem Pesaran, July 2016
Abstract: The recent plunge in oil prices has brought into question the generally accepted view that lower oil prices are good for the US and the global economy. In this paper, using a quarterly multicountry econometric model, we first show that a fall in oil prices tends relatively quickly to lower interest rates and inflation in most countries, and increase global real equity prices. The effects on real output are positive, although they take longer to materialize (around 4 quarters after the shock). We then reexamine the effects of low oil prices on the US economy over different subperiods using monthly observations on real oil prices, real equity prices and real dividends. We confirm the perverse positive relationship between oil and equity prices over the period since the 2008 financial crisis highlighted in the recent literature, but show that this relationship has been unstable when considered over the longer time period of 19462016. In contrast, we find a stable negative relationship between oil prices and real dividends which we argue is a better proxy for economic activity (as compared to equity prices). On the supply side, the effects of lower oil prices differ widely across the different oil producers, and could be perverse initially, as some of the major oil producers try to compensate their loss of revenues by raising production. Taking demand and supply adjustments to oil price changes as a whole, we conclude that oil markets equilibrate but rather slowly, with large episodic swings between low and high oil prices.
JEL Classifications: C32, E17, E32, F44, F47, O51, Q43.
Key Words: Oil prices, equity prices, dividends, economic growth, oil supply, global oil markets, and international business cycle.
Full Text:http://www.econ.cam.ac.uk/peoplefiles/emeritus/mhp1/wp16/MP_Oil_Prices_&_Global_Economy_160703.pdf

"Doublequestion Survey Measures for the Analysis of Financial Bubbles and Crashes", by M. Hashem Pesaran and Ida Johnsson, December 2016, revised January 2017
Abstract: This paper proposes a new doublequestion survey whereby an individual is presented with two sets of questions; one on beliefs about current asset values and another on price expectations. A theoretical asset pricing model with heterogeneous agents is advanced and the existence of a negative relationship between price expectations and asset valuations is established, which is tested using survey results on equity, gold and house prices. Leading indicators of bubbles and crashes are proposed and their potential value is illustrated in the context of a dynamic panel regression of realized house price changes across a number of key MSAs in the US.
JEL Classifications: C83, D84, G12, G14.
Key Words: Price expectations, bubbles and crashes, house prices, belief valuations.
Full Text: http://www.econ.cam.ac.uk/peoplefiles/emeritus/mhp1/wp17/Pesaran_and_Johnsson_Doublequestion_2_January_2017.pdf
Suppliment: http://www.econ.cam.ac.uk/peoplefiles/emeritus/mhp1/wp17/PJ_Double_Q_Supplement_2_January_2017.pdf
Data: http://www.econ.cam.ac.uk/peoplefiles/emeritus/mhp1/wp17/Double_Q_survey_data_Aug_2012Jan_2013.zip
Replication: http://www.econ.cam.ac.uk/peoplefiles/emeritus/mhp1/wp17/Double_Q_Survey_Replication.zip

"Doublequestion Survey Measures for the Analysis of Financial Bubbles and Crashes", by M. Hashem Pesaran and Ida Johnsson, December 2016
Abstract: This paper proposes a new doublequestion survey method that elicits information about how individuals subjective belief valuations are compared and related to their price expectations. An individual respondent is presented with two sets of questions, one that asks about his/her belief regarding the value of an asset (whether it is over or undervalued), and another regarding his/her expectations of the future price of that asset. Responses to these two questions are then used to measure the extent to which prices are likely to move towards or away from the subjectively perceived fundamental values. Using a theoretical asset pricing model with heterogenous agents we show that there exists a negative relationship between the agents expectations of price changes and their asset valuation. Double question surveys on equity, gold and house prices provide evidence in support of such relationships, particularly in the case of house price expectations. The effects of demographic factors, such as sex, age, education, ethnicity, and income are also investigated. It is shown that for house price expectations such demographic factors cease to be statistically significant once we condition on the respondents' location and their asset valuation indicator. The results of the doublequestion surveys are then used to construct leading bubble and crash indicators, and their potential value is illustrated in the context of a dynamic panel regression of realized house price changes across a number of key Metropolitan Statistical Areas in the US.
JEL Classifications: C83, D84, G12, G14.
Key Words: Price expectations, bubbles and crashes, house prices, belief valuations.
Full Text: http://www.econ.cam.ac.uk/peoplefiles/emeritus/mhp1/wp16/Pesaran_and_Johnsson_Double_Question_Surveys_Dec_2016_SSRNid2880856.pdf

"Big Data Analytics: A New Perspective", by Alexander Chudik, George Kapetanios and M. Hashem Pesaran, February 2016
Abstract: Model specification and selection are recurring themes in econometric analysis. Both topics become considerably more complicated in the case of largedimensional data sets where the set of specification possibilities can become quite large. In the context of linear regression models, penalised regression has become the de facto benchmark technique used to trade off parsimony and fit when the number of possible covariates is large, often much larger than the number of available observations. However, issues such as the choice of a penalty function and tuning parameters associated with the use of penalized regressions remain contentious. In this paper, we provide an alternative approach that considers the statistical significance of the individual covariates one at a time, whilst taking full account of the multiple testing nature of the inferential problem involved. We refer to the proposed method as One Covariate at a Time Multiple Testing (OCMT) procedure The OCMT has a number of advantages over the penalised regression methods: It is based on statistical inference and is therefore easier to interpret and relate to the classical statistical analysis, it allows working under more general assumptions, it is computationally simple and considerably faster, and it performs better in small samples for almost all of the five different sets of experiments considered in this paper. Despite its simplicity, the theory behind the proposed approach is quite complicated. We provide extensive theoretical and Monte Carlo results in support of adding the proposed OCMT model selection procedure to the toolbox of applied researchers.
JEL Classifications: C52, C55
Key Words: One covariate at a time, multiple testing, model selection, high dimensionality, penalised regressions, boosting, Monte Carlo experiments.
Full Text: http://www.econ.cam.ac.uk/peoplefiles/emeritus/mhp1/wp16/ChudikKapetaniosPesaran_BDA_11Feb2016_main.pdf
Supplement 1: http://www.econ.cam.ac.uk/peoplefiles/emeritus/mhp1/wp16/TheorySupplement_to_ChudikKapetaniosPesaran_BDA_11Feb2016.pdf
Supplement 2: http://www.econ.cam.ac.uk/peoplefiles/emeritus/mhp1/wp16/MC_Supplement_to_ChudikKapetaniosPesaran_BDA_05Feb2016.pdf

"CountrySpecific Oil Supply Shocks and the Global Economy: A Counterfactual Analysis", by Kamiar Mohaddes and M. Hashem Pesaran, forthcoming in Energy Economics, July 2016.
Abstract: This paper investigates the global macroeconomic consequences of countryspecific oilsupply shocks. Our contribution is both theoretical and empirical. On the theo retical side, we develop a model for the global oil market and integrate this within a compact quarterly model of the global economy to illustrate how our multicountry approach to modelling oil markets can be used to identify countryspecific oilsupply shocks. On the empirical side, estimating the GVAROil model for 27 countries/regions over the period 1979Q2 to 2013Q1, we show that the global economic implications of oilsupply shocks (due to, for instance, sanctions, wars, or natural disasters) vary considerably depending on which country is subject to the shock. In particular, we find that adverse shocks to Iranian oil output are neutralized in terms of their effects on the global economy (real outputs and financial markets) mainly due to an increase in Saudi Arabian oil production. In contrast, a negative shock to oil supply in Saudi Arabia leads to an immediate and permanent increase in oil prices, given that the loss in Saudi Arabian production is not compensated for by the other oil producers. As a result, a Saudi Arabian oil supply shock has significant adverse effects for the global economy with real GDP falling in both advanced and emerging economies, and large losses in real equity prices worldwide.
JEL Classifications: C32, E17, F44, F47, O53, Q43.
Key Words: Countryspecific oil supply shocks, identification of shocks, oil sanctions, oil prices, global oil markets, Iran, Saudi Arabia, international business cycle, Global VAR (GVAR), interconnectedness, impulse responses.
Full Text: http://www.econ.cam.ac.uk/peoplefiles/emeritus/mhp1/fp16/MP_GVAR_July2015EE.pdf
Data: http://www.econ.cam.ac.uk/peoplefiles/emeritus/mhp1/fp16/MP_GVAR_Data.zip

"CountrySpecific Oil Supply Shocks and the Global Economy: A Counterfactual Analysis", by Kamiar Mohaddes and M. Hashem Pesaran, May 2015
Abstract: This paper investigates the global macroeconomic consequences of countryspecific oilsupply shocks. Our contribution is both theoretical and empirical. On the theoretical side, we develop a model for the global oil market and integrate this within a compact quarterly model of the global economy to illustrate how our multicountry approach to modelling oil markets can be used to identify countryspecific oilsupply shocks. On the empirical side, estimating the GVAROil model for 27 countries/regions over the period 1979Q2 to 2013Q1, we show that the global economic implications of oilsupply shocks (due to, for instance, sanctions, wars, or natural disasters) vary considerably depending on which country is subject to the shock. In particular, we find that adverse shocks to Iranian oil output are neutralized in terms of their effects on the global economy (real outputs and financial markets) mainly due to an increase in Saudi Arabian oil production. In contrast, a negative shock to oil supply in Saudi Arabia leads to an immediate and permanent increase in oil prices, given that the loss in Saudi Arabian production is not compensated for by the other oil producers. As a result, a Saudi Arabian oil supply shock has significant adverse effects for the global economy with real GDP falling in both advanced and emerging economies, and large losses in real equity prices worldwide.
JEL Classifications: C32, E17, F44, F47, O53, Q43.
Key Words: Countryspecific oil supply shocks, identification of shocks, oil sanctions, oil prices, global oil markets, Iran, Saudi Arabia, international business cycle, Global VAR (GVAR), interconnectedness, impulse responses.
Full Text: http://www.econ.cam.ac.uk/peoplefiles/emeritus/mhp1/wp15/MP_GVAR_20_June_2015.pdf

"A Multiple Testing Approach to the Regularisation of Large Sample Correlation Matrices", by Natalia Bailey, M. Hashem Pesaran and L. Vanessa Smith, CAFE Research Paper No. 14.05, May 2014, revised November 2015
Abstract: This paper proposes a regularisation method for the estimation of large covariance matrices that uses insights from the multiple testing (MT) literature. The approach tests the statistical significance of individual pairwise correlations and sets to zero those elements that are not statistically significant, taking account of the multiple testing nature of the problem. By using the inverse of the normal distribution at a predetermined significance level, it circumvents the challenge of estimating the theoretical constant arising in the rate of convergence of existing thresholding estimators, and hence it is easy to implement and does not require crossvalidation. The MT estimator of the sample correlation matrix is shown to be consistent in the spectral and Frobenius norms, and in terms of support recovery, so long as the true covariance matrix is sparse. The performance of the proposed MT estimator is compared to a number of other estimators in the literature using Monte Carlo experiments. It is shown that the MT estimator performs well and tends to outperform the other estimators, particularly when the cross section dimension, N, is larger than the time series dimension, T.
JEL Classifications: C13, C58.
Key Words: Sparse correlation matrices, Highdimensional data, Multiple testing, Thresholding, Shrinkage.
Full Text: http://www.econ.cam.ac.uk/peoplefiles/emeritus/mhp1/wp15/BPS_5Nove2015.pdf
Supplementary Material: http://www.econ.cam.ac.uk/peoplefiles/emeritus/mhp1/wp15/BPS_Supplement_5November2015.pdf

"An Exponential Class of Dynamic Binary Choice Panel Data Models with Fixed Effects", by Majid M. AlSadoon, Tong Li and M. Hashem Pesaran, CESifo Working Paper No. 4033, October 2012, revised January 2016
Abstract: This paper proposes an exponential class of dynamic binary choice panel data models for the analysis of short T( time dimension) large N (cross section dimension) panel data sets that allows for unobserved heterogeneity (fixed effects) to be arbitrarily correlated with the covariates. The paper derives moment conditions that are in variant to the fixed effects which are then used to identify and estimate the parameters of the model. Accordingly, GMM estimators are proposed that are consistent and asymptotically normally distributed at the rootN rate. We also study the conditional likelihood approach, and show that under exponential specification it can identify the effect of state dependence but not the effects of other covariates. Monte Carlo experiments show satisfactory nite sample performance for the proposed estimators, and investigate their robustness to missspecification..
JEL Classifications: C23, C25
Key Words: Dynamic Discrete Choice, Fixed Effects, Panel Data, GMM, CMLE.
Full Text: http://www.econ.cam.ac.uk/peoplefiles/emeritus/mhp1/wp16/AlSaddonTongPesaranJan2016.pdf

"Estimation of Timeinvariant Effects in Static Panel Data Models", by M. Hashem Pesaran and Qiankun Zhou, January 2015
Abstract: This paper proposes the Fixed Effects Filtered (FEF) and Fixed Effects Filtered instrumental variable (FEFIV) estimators for estimation and inference in the case of timeinvariant effects in static panel data models when N is large and T is fixed. It is shown that the FEF and FEFIV estimators are pNconsistent, and asymptotically normally distributed. The FEF estimator is compared with the Fixed Effects Vector Decomposition (FEVD) estimator proposed by Plumper and Troeger (2007) and conditions under which the two estimators are equivalent are established. It is also shown that the variance estimator proposed for FEVD estimator is inconsistent and its use could lead to misleading inference. Alternative variance estimators are proposed for both FEF and FEFIV estimators which are shown to be consistent under fairly general conditions. The small sample properties of the FEF and FEFIV estimators are investigated by Monte Carlo experiments, and it is shown that FEF has smaller bias and RMSE, unless an intercept is included in the second stage of the FEVD procedure which renders the FEF and FEVD estimators identical. The FEVD procedure, however, results in substantial size distortions since it uses incorrect standard errors. We also compare the FEFIV estimator with the estimator proposed by Hausman and Taylor (1981), when one of the timeinvariant regressors is correlated with the fixed effects. Both FEF and FEFIV estimators are shown to be robust to error variance heteroskedasticity and residual serial correlation.
JEL Classifications: C01, C23, C33.
Key Words: Static panel data models, Timeinvariant effects, Fixed Effects Filtered estimator, Fixed Effects Filtered instrumental variables estimator.
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/wp14/PesaranZhou_Timeinvariantestimation_Sep52014.pdf

"LongRun Effects in Large Heterogenous Panel Data Models with CrossSectionally Correlated Errors", by Alexander Chudik, Kamiar Mohaddes, M. Hashem Pesaran and Mehdi Raissi, forthcoming in Advances in Econometrics, V36 Essays in Honor of Aman Ullah, 2016.
Abstract: This paper develops a crosssectionally augmented distributed lag (CSDL) approach to the estimation of longrun effects in large dynamic heterogeneous panel data models with crosssectionally dependent errors. The asymptotic distribution of the CSDL estimator is derived under coeficient heterogeneity in the case where the time dimension (T) and the crosssection dimension (N) are both large. The CSDL approach is compared with more standard panel data estimators that are based on autoregressive distributed lag (ARDL) specifications. It is shown that unlike the ARDL type estimator, the CSDL estimator is robust to misspecification of dynamics and error serial correlation. The theoretical results are illustrated with small sample evidence obtained by means of Monte Carlo simulations, which suggest that the performance of the CSDL approach is often superior to the alternative panel ARDL estimates, particularly when T is not too large and lies in the range of 30 to 50.
JEL Classifications: C23.
Key Words: Longrun relationships, estimation and inference, panel distributed lags, large dynamic heterogeneous panels, crosssection dependence.
Full Text: http://www.econ.cam.ac.uk/peoplefiles/emeritus/mhp1/fp16/CSDL_30October2015.pdf

"Theory and Practice of GVAR Modeling", by Alexander Chudik, and M. Hashem Pesaran, SSRN Research Paper Series No. 14.04, forthcoming in the Journal of Economic Surveys, September 2014.
Abstract: The Global Vector Autoregressive (GVAR) approach has proven to be a very useful approach to analyze interactions in the global macroeconomy and other data networks where both the crosssection and the time dimensions are large. This paper surveys the latest developments in the GVAR modeling, examining both the theoretical foundations of the approach and its numerous empirical applications. We provide a synthesis of existing literature and highlight areas for future research.
JEL Classifications: C32, E17.
Key Words: Global VAR, global macroeconometric modelling, global interdependencies, policy simulations.
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/fp14/CPGVARSurveysSept2014.pdf

"Business Cycle Effects of Credit and Technology Shocks in a DSGE Model with Firm Default", by M. Hashem Pesaran and TengTeng Xu, CWPE Working paper. No. 1159, CESifo Working Paper No. 3609, IZA Discussion Paper No. 6027, October 2011, under revision
Abstract: This paper proposes a theoretical framework to analyze the relationship between credit shocks, firms defaults and volatility, and to study the impact of credit shocks on business cycle dynamics. Firms are identical ex ante but differ ex post due to different realizations of firm specific technology shocks, possibly leading to default by some firms. The paper advances a new modelling approach for the analysis of firm defaults and financial intermediation that takes account of the financial implications of such defaults for both households and banks. Results from a calibrated version of the model suggest that, in the steady state, firm's default probability rises with firm's leverage ratio, and the level of uncertainties in the economy. A positive credit shock, defined as a rise in the loan to deposit ratio, increases output, consumption, hours and productivity, and reduces the spread between loan and deposit rates. The effects of the credit shock tend to be highly persistent even without price rigidities and habit persistence in consumption behaviour.
JEL Classifications: E32, E44, G21.
Key Words: Bank Credit, Financial Intermediation, Firm Heterogeneity and Defaults, Interest Rate Spread, Real Financial Linkages.
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/wp13/MacroCredit_PesaranXuFeb2013.pdf
Supplement: http://www.econ.cam.ac.uk/emeritus/mhp1/wp11/MacroCredit_ 5Oct2011_Supplement.pdf

"An Exponential Class of Dynamic Binary Choice Panel Data Models with Fixed Effects", by Majid M. AlSadoon, Tong Li and M. Hashem Pesaran, CESifo Working Paper No. 4033, October 2012, revised August 2014
Abstract: This paper develops a model for dynamic binary choice panel data that allows for unobserved heterogeneity to be arbitrarily correlated with covariates. The model is of the exponential type. We derive moment conditions that enable us to eliminate the unobserved heterogeneity term and at the same time to identify the parameters of the model. We then propose GMM estimators that are consistent and asymptotically normally distributed at the rootN rate. We also study the conditional likelihood approach, which can only identify the effect of state dependence in our case. Monte Carlo experiments demonstrate the finite sample performance of our estimators.
JEL Classifications: C23, C25
Key Words: Dynamic Discrete Choice, Fixed Effects, Panel Data, GMM, CMLE.
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/wp14/DBCAugust14.pdf

"Robust Standard Errors in Transformed Likelihood Estimation of Dynamic Panel Data Models with CrossSectional Heteroskedasticity", by Kazuhiko Hayakawa and M. Hashem Pesaran, CWPE Working Paper No. 1224, IZA Discussion Paper 6583, Cesifo Working Paper No.3850, forthcoming in Journal of Econometrics, March 2015.
Abstract: This paper extends the transformed maximum likelihood approach for estimation of dynamic panel data models by Hsiao, Pesaran, and Tahmiscioglu (2002) to the case where the errors are crosssectionally heteroskedastic. This extension is not trivial due to the incidental parameters problem and its implications for estimation and inference. We approach the problem by working with a misspecified homoskedastic model, and then show that the transformed maximum likelihood estimator continues to be consistent even in the presence of crosssectional heteroskedasticity. We also obtain standard errors that are robust to crosssectional heteroskedasticity of unknown form. By means of Monte Carlo simulations, we investigate the finite sample behavior of the transformed maximum likelihood estimator and compare it with various GMM estimators proposed in the literature. Simulation results reveal that, in terms of median absolute errors and accuracy of inference, the transformed likelihood estimator outperforms the GMM estimators in almost all cases.
JEL Classifications: C12, C13, C23
Key Words: Dynamic Panels, Crosssectional heteroskedasticity, Monte Carlo simulation, Transformed MLE, GMM estimation.
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/fp15/Hayakawa_Pesaran_robustML_R2_04Nov2014.pdf
Matlab Code: http://www.econ.cam.ac.uk/emeritus/mhp1/wp12/MatlabcodeanddataforTransMLHayakawaandPesaran2012.zip
Supplementary Data: http://www.econ.cam.ac.uk/emeritus/mhp1/fp15/Supplement_04Nov2014.pdf

"Common Correlated Effects Estimation of Heterogeneous Dynamic Panel Data Models with Weakly Exogenous Regressors", by Alexander Chudik, and M. Hashem Pesaran,CESifo Working Paper No. 4232 and CAFE Research Paper No. 13.14, IZA Discussion Paper No. 6618, forthcoming in the Journal of Econometrics July 2014.
Abstract: This paper extends the Common Correlated Effects (CCE) approach developed by Pesaran (2006) to heterogeneous panel data models with lagged dependent variable and/or weakly exogenous regressors. We show that the CCE mean group estimator continues to be valid but the following two conditions must be satisfied to deal with the dynamics: a sufficient number of lags of cross section averages must be included in individual equations of the panel, and the number of cross section averages must be at least as large as the number of unobserved common factors. We establish consistency rates, derive the asymptotic distribution, suggest using covariates to deal with the effects of multiple unobserved common factors, and consider jackknife and recursive demeaning bias correction procedures to mitigate the small sample time series bias. Theoretical findings are accompanied by extensive Monte Carlo experiments, which show that the proposed estimators perform well so long as the time series dimension of the panel is sufficiently large.
JEL Classifications: C31, C33
Key Words: Large panels, lagged dependent variable, cross sectional dependence, coefficient heterogeneity, estimation and inference, common correlated effects, unobserved common factors.
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/fp14/CP_DynamicCCE_3July2014.pdf
Supplement: http://www.econ.cam.ac.uk/emeritus/mhp1/fp14/Supplement_28Jan2014.pdf

"Testing Weak CrossSectional Dependence in Large Panels", by M. Hashem Pesaran, January 2012, CWPE Working Paper No. 1208, IZA Discussion Paper No. 6432, forthcoming in Econometric Reviews
Abstract: This paper considers testing the hypothesis that errors in a panel data model are weakly cross sectionally dependent, using the exponent of crosssectional dependence , introduced recently in Bailey, Kapetanios and Pesaran (2012). It is shown that the implicit null of the CD test depends on the relative expansion rates of N and T. When T = O , for some , then the implicit null of the CD test is given by , which gives , when N and T tend to infinity at the same rate such that T/N , with being a finite positive constant. It is argued that in the case of large N panels, the null of weak dependence is more appropriate than the null of independence which could be quite restrictive for large panels. Using Monte Carlo experiments, it is shown that the CD test has the correct size for values of in the range [0, 1/4], for all combinations of N and T, and irrespective of whether the panel contains lagged values of the dependent variables, so long as there are no major asymmetries in the error distribution.
JEL Classifications: C12, C13, C3
Key Words: Exponent of crosssectional dependence, Diagnostic tests, Panel data models, Dynamic heterogenous panels.
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/fp13/PesaranWCDTest11Jan2013.pdf

"Debt, Inflation and Growth: Robust Estimation of LongRun Effects in Dynamic Panel Data Models", by Alexander Chudik, Kamiar Mohaddes, M. Hashem Pesaran, and Mehdi Raissi, November 2013
Abstract: This paper investigates the longrun effects of public debt and inflation on economic growth. Our contribution is both theoretical and empirical. On the theoretical side, we develop a crosssectionally augmented distributed lag (CSDL) approach to the estimation of longrun effects in dynamic heterogeneous panel data models with crosssectionally dependent errors. The relative merits of the CSDL approach and other existing approaches in the literature are discussed and illustrated with small sample evidence obtained by means of Monte Carlo simulations. On the empirical side, using data on a sample of 40 countries over the 19652010 period, we find significant negative longrun effects of public debt and inflation on growth. Our results indicate that, if the debt to GDP ratio is raised and this increase turns out to be permanent, then it will have negative effects on economic growth in the long run. But if the increase is temporary, then there are no longrun growth effects so long as debt to GDP is brought back to its normal level. We do not find a universally applicable threshold effect in the relationship between public debt and growth. We only find statistically significant threshold effects in the case of countries with rising debt to GDP ratios.
JEL Classifications: C23, E62, F34, H6
Key Words: Longrun relationships, estimation and inference, large dynamic heterogeneous panels, crosssection dependence, debt, inflation and growth, debt overhang
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/wp13/CMPR_18November2013.pdf
Video: http://youtu.be/5Zms8SAjsbc
Matlab Codes for the CSDL Estimators: http://www.econ.cam.ac.uk/peoplefiles/cto/km418/CMPR_CSDL.zip
Data and Stata Do File: http://www.econ.cam.ac.uk/peoplefiles/cto/km418/CMPR_Data.zip

"A multicountry approach to forecasting output growth using PMIs", by Alexander Chudik, Valerie Grossmanz and M. Hashem Pesaran, November 2014
Abstract: This paper derives new theoretical results for forecasting with Global VAR (GVAR) models. It is shown that the presence of a strong unobserved common factor can lead to an undetermined GVAR model. To solve this problem, we propose augmenting the GVAR with additional proxy equations for the strong factors and establish conditions under which forecasts from the augmented GVAR model (AugGVAR) uniformly converge in probability (as the panel dimensions N,T [code] ∞ such that N/T → k for some 0 < k < ∞) to the infeasible optimal forecasts obtained from a factoraugmented highdimensional VAR model. The small sample properties of the proposed solution are investigated by Monte Carlo experiments as well as empirically. In the empirical part, we investigate the value of the information content of Purchasing Managers Indices (PMIs) for forecasting global (48 countries) growth, and compare forecasts from Aug GVAR models with a number of datarich forecasting methods, including Lasso, Ridge, partial least squares and factorbased methods. It is found that (a) regardless of the forecasting meth ods considered, PMIs are useful for nowcasting, but their value added diminishes quite rapidly with the forecast horizon, and (b) AugGVAR forecasts do as well as other datarich forecasting techniques for short horizons, and tend to do better for longer forecast horizons.
JEL Classifications: C53, E37.
Key Words: Global VARs, Highdimensional VARs, Augmented GVAR, Forecasting, Nowcasting, Datarich methods, GDP and PMIs
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/wp14/CGP_GDPnowcasting_10November2014.pdf

"Is There a Debtthreshold Effect on Output Growth?", by Alexander Chudik, Kamiar Mohaddes, M. Hashem Pesaran, and Mehdi Raissi, July 2015
Abstract: This paper studies the longrun impact of public debt expansion on economic growth and investigates whether the debtgrowth relation varies with the level of indebtedness. Our contribution is both theoretical and empirical. On the theoretical side, we develop tests for threshold effects in the context of dynamic heterogeneous panel data models with crosssectionally dependent errors and illustrate, by means of Monte Carlo experiments, that they perform well in small samples. On the empirical side, using data on a sample of 40 countries (grouped into advanced and developing) over the 19652010 period, we find no evidence for a universally applicable threshold effect in the relationship between public debt and economic growth, once we account for the impact of global factors and their spillover effects. Regardless of the threshold, however, we find significant negative longrun effects of public debt buildup on output growth. Provided that public debt is on a downward trajectory, a country with a high level of debt can grow just as fast as its peers.
JEL Classifications: C23, E62, F34, H6
Key Words: Panel tests of threshold effects, longrun relationships, estimation and inference, large dynamic heterogeneous panels, crosssection dependence, debt, and inflation.
Full Text: http://www.econ.cam.ac.uk/peoplefiles/emeritus/mhp1/wp15/CMPR_July3_2015.pdf
Supplement: http://www.econ.cam.ac.uk/peoplefiles/emeritus/mhp1/wp15/Supplement_03July2015.pdf

"A Multiple Testing Approach to the Regularisation of Large Sample Correlation Matrices", by Natalia Bailey, M. Hashem Pesaran and L. Vanessa Smith, CAFE Research Paper No. 14.05, May 2014, revised January 2015
Abstract: This paper proposes a novel regularisation method for the estimation of large covariance matrices, using insights from the multiple testing (MT) literature. The method tests the statistical significance of individual pairwise correlations and sets to zero those elements that are not statistically significant, taking account of the multiple testing nature of the problem. The procedure is straightforward to implement and is readily adapted to deal with nonGaussian observations. By using the inverse of the normal distribution at a predetermined significance level, it circumvents the challenge of evaluating the theoretical constant arising in the rate of convergence of existing thresholding estimators, and hence does not require crossvalidation. We compare the small sample performance of the proposed MT estimator to a number of other regularisation techniques in the literature using Monte Carlo experiments. We find that the MT estimator performs well and tends to outperform the other estimators, particularly when the crosssectional dimension, N, is larger than the time series dimension, T. If the inverse covariance matrix is also of interest, then we propose a shrinkage version of the MT estimator that ensures positive definiteness.
JEL Classifications: C13, C58.
Key Words: Sparse correlation matrices, Highdimensional data, Multiple testing, Thresholding, Shrinkage.
Full Text: http://www.econ.cam.ac.uk/peoplefiles/emeritus/mhp1/wp15/BPS_22Jan2015.pdf
Supplementary Material: http://www.econ.cam.ac.uk/peoplefiles/emeritus/mhp1/wp15/BPS_Supplement_22Jan2015.pdf

"LongRun Effects in Large Heterogenous Panel Data Models with CrossSectionally Correlated Errors", by Alexander Chudik, Kamiar Mohaddes, M. Hashem Pesaran and Mehdi Raissi, January 2015
Abstract: This paper develops a crosssectionally augmented distributed lag (CSDL) approach to the estimation of longrun effects in large dynamic heterogeneous panel data models with cross sectionally dependent errors. The asymptotic distribution of the CSDL estimator is derived under coefficient heterogeneity in the case where the time dimension (T) and the crosssection dimension (N) are both large. The CSDL approach is compared with more standard panel data estimators that are based on autoregressive distributed lag (ARDL) specifications. It is shown that unlike the ARDL type estimator, the CSDL estimator is robust to misspecification of dynamics and error serial correlation. The theoretical results are illustrated with small sample evidence obtained by means of Monte Carlo simulations, which suggest that the performance of the CSDL approach is often superior to the alternative panel ARDL estimates particularly when T is not too large and lies in the range of [code].
JEL Classifications: C23.
Key Words: Longrun relationships, estimation and inference, large dynamic heterogeneous panels, crosssection dependence.
Full Text: http://www.econ.cam.ac.uk/peoplefiles/emeritus/mhp1/wp15/CSDL_16January2015.pdf

"Robust Standard Errors in Transformed Likelihood Estimation of Dynamic Panel Data Models with CrossSectional Heteroskedasticity", by Kazuhiko Hayakawa and M. Hashem Pesaran, CWPE Working Paper No. 1224, IZA Discussion Paper 6583, Cesifo Working Paper No.3850, April 2012, revised January 2014
Abstract: This paper extends the transformed maximum likelihood approach for estimation of dynamic panel data models by Hsiao, Pesaran, and Tahmiscioglu (2002) to the case where the errors are crosssectionally heteroskedastic. This extension is not trivial due to the incidental parameters problem and its implications for estimation and inference. We approach the problem by working with a misspecified homoskedastic model, and then show that the transformed maximum likelihood estimator continues to be consistent even in the presence of crosssectional heteroskedasticity. We also obtain standard errors that are robust to crosssectional heteroskedasticity of unknown form. By means of Monte Carlo simulations, we investigate the finite sample behavior of the transformed maximum likelihood estimator and compare it with various GMM estimators proposed in the literature. Simulation results reveal that, in terms of median absolute errors and accuracy of inference, the transformed likelihood estimator outperforms the GMM estimators in almost all cases.
JEL Classifications: C12, C13, C23
Key Words: Dynamic Panels, Crosssectional heteroskedasticity, Monte Carlo simulation, Transformed MLE, GMM estimation.
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/wp14/Hayakawa_Pesaran_robustML_R1_27Jan 2014.pdf
Matlab Code: http://www.econ.cam.ac.uk/emeritus/mhp1/wp12/MatlabcodeanddataforTransMLHayakawaandPesaran2012.zip

"Exponent of Crosssectional Dependence: Estimation and Inference", by Natalia Bailey, George Kapetanios and M. Hashem Pesaran, November 2013, revised December 2014
Abstract: In this paper we provide a characterization of the degree of crosssectional dependence in a two dimensional array, [code] in terms of the rate at which the variance of the crosssectional average of the observed data varies with N. We show that under certain conditions this is equivalent to the rate at which the largest eigenvalue of the covariance matrix of [code] rises with N. We represent the degree of crosssectional dependence by , defined by the standard deviation, Std [code], where [code] is a simple crosssectional average of [code]. We refer to as the `exponent of crosssectional dependence', and show how it can be consistently estimated for values of > 1/2. We propose bias corrected estimators, derive their asymptotic properties and consider a number of extensions. We include a detailed Monte Carlo simulation study supporting the theoretical results. We also provide a number of empirical applications investigating the degree of interlinkages of real and nancial variables in the global economy, the extent to which macroeconomic variables are interconnected across and within countries, and present recursive estimates of applied to excess returns on securities included in the Standard and Poor 500 index.
JEL Classifications: C21, C32
Key Words: Cross correlations, Crosssectional dependence, Crosssectional averages, Weak and strong factor models
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/wp14/BKP_Cross_Section_Exponent_3(main)_Dec_2014.pdf
Supplementary Appendices: http://www.econ.cam.ac.uk/emeritus/mhp1/wp14/BKP_Cross_Section_Exponent_3(suppl)_Dec_2014.pdf

"A Multiple Testing Approach to the Regularisation of Large Sample Correlation Matrices", by Natalia Bailey, M. Hashem Pesaran and L. Vanessa Smith, CAFE Research Paper No. 14.05, May 2014
Abstract: This paper proposes a novel regularisation method for the estimation of large covariance matrices, which makes use of insights from the multiple testing literature. The method tests the statistical significance of individual pairwise correlations and sets to zero those elements that are not statistically significant, taking account of the multiple testing nature of the problem. The procedure is straightforward to implement, and does not require cross validation. By using the inverse of the normal distribution at a predetermined significance level, it circumvents the challenge of evaluating the theoretical constant arising in the rate of convergence of existing thresholding estimators. We compare the performance of our multiple testing (MT) estimator to a number of thresholding and shrinkage estimators in the literature in a detailed Monte Carlo simulation study. Results show that our MT estimator performs well in a number of different settings and tends to outperform other estimators, particularly when the crosssectional dimension, N, is larger than the time series dimension, T: If the inverse covariance matrix is of interest then we recommend a shrinkage version of the MT estimator that ensures positive definiteness.
JEL Classifications: C13, C58.
Key Words: Sparse correlation matrices, Highdimensional data, Multiple testing, Thresholding, Shrinkage.
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/wp14/BPS_19May14.pdf

"Constructing MultiCountry Rational Expectations Models", by Stephane Dees, M. Hashem Pesaran, Ron P. Smith and L. Vanessa Smith, CESifo Working Papers No. 3081, October 2012, forthcoming in Oxford Bulletin of Economics and Statistics.
Abstract: This paper considers some of the technical issues involved in using the GVAR approach to construct a multicountry rational expectations, RE, model and illustrates them with a new Keynesian model for 33 countries estimated with quarterly data over the period 19802011. The issues considered are: the measurement of steady states; the determination of exchange rates and the specification of the shortrun countryspecific models; the identification and estimation of the model subject to the theoretical constraints required for a determinate rational expectations solution; the solution of a large RE model; the structure and estimation of the covariance matrix; and the simulation of shocks. The model used as an illustration shows that global demand and supply shocks are the most important drivers of output, inflation and interest rates in the long run. By contrast, monetary or exchange rate shocks have only a shortrun impact in the evolution of the world economy. The paper also shows the importance of international connections, directly as well as indirectly through spillover effects. Overall, ignoring global interconnections as countryspecific models do, could give rise to misleading conclusions.
JEL Classifications: C32, E17, F37, F42
Key Words: Global VAR (GVAR), Multicountry New Keynesian (MCNK) models, supply shocks, demand shocks, monetary policy shocks
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/fp13/DPSS_26June13.pdf
Supplement: http://www.econ.cam.ac.uk/emeritus/mhp1/fp13/DPPS_MCNK_Supplement_26June2013.pdf
Readme Data: http://www.econ.cam.ac.uk/emeritus/mhp1/wp10/ReadmeDataDPSS(2010).pdf
Transformed Data: http://www.econ.cam.ac.uk/emeritus/mhp1/wp10/TransformedData(1979Q12006Q4).zip
Source Data: http://www.econ.cam.ac.uk/emeritus/mhp1/wp10/SourceData(1979Q12006Q4).zip

"Large Panel Data Models with CrossSectional Dependence: A Survey", by Alexander Chudik, and M. Hashem Pesaran, CESifo WP Number 4371, August 2013, forthcoming in B. H. Baltagi (Ed.), The Oxford Handbook on Panel Data. Oxford University Press.
Abstract: This paper provides an overview of the recent literature on estimation and inference in large panel data models with crosssectional dependence. It reviews panel data models with strictly exogenous regressors as well as dynamic models with weakly exogenous regressors. The paper begins with a review of the concepts of weak and strong crosssectional dependence, and discusses the exponent of crosssectional dependence that characterizes the different degrees of crosssectional dependence. It considers a number of alternative estimators for static and dynamic panel data models, distinguishing between factor and spatial models of crosssectional dependence. The paper also provides an overview of tests of independence and weak crosssectional dependence.
JEL Classifications: C31, C33
Key Words: Large panels, weak and strong crosssectional dependence, factor structure, spatial dependence, tests of crosssectional dependence.
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/wp13/ChudikPesaranSurevyCSD13August2013.pdf

"Tests of Policy Ineffectiveness in Macroeconometrics", by M. Hashem Pesaran and Ron P. Smith, CAFE Research Paper No. 14.07, June 2014
Abstract: This paper proposes tests of policy ineffectiveness in the context of macroeconometric rational expectations models. It is assumed that there is a policy intervention that takes the form of changes in the parameters of a policy rule, and that there are sufficient observations before and after the intervention. The test is based on the difference between the realisations of the outcome variable of interest and counterfactuals based on no policy intervention, using only the preintervention parameter estimates, and in consequence the Lucas Critique does not apply. The paper develops tests of policy ineffectiveness for a full structural model, with and without exogenous, policy or nonpolicy, variables. Asymptotic distributions of the proposed tests are derived both when the post intervention sample is fixed as the preintervention sample expands, and when both samples rise jointly but at different rates. The performance of the test is illustrated by a simulated policy analysis of a three equation New Keynesian Model, which shows that the test size is correct but the power may be low unless the model includes exogenous variables, or if the policy intervention changes the steady states, such as the inflation target.
JEL Classifications: C18, C54, E65.
Key Words: Counterfactuals, policy analysis, policy ineffectiveness test, macroeconomics.
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/wp14/PSonPI_15June2014.pdf

"A Two Stage Approach to Spatiotemporal Analysis with Strong and Weak CrossSectional Dependence", by Natalia Bailey, Sean Holly, and M. Hashem Pesaran, December 2013, revised July 2014
Abstract: An understanding of the spatial dimension of economic and social activity requires methods that can separate out the relationship between spatial units that is due to the effect of common factors from that which is purely spatial even in an abstract sense. The same applies to the empirical analysis of networks in general. We use cross unit averages to extract common factors (viewed as a source of strong crosssectional dependence) and compare the results with the principal components approach widely used in the literature. We then apply multiple testing procedures to the defactored observations in order to determine significant bilateral correlations (signifying connections) between spatial units and compare this to an approach that just uses distance to determine units that are neighbours. We apply these methods to real house price changes at the level of Metropolitan Statistical Areas in the USA, and estimate a heterogeneous spatiotemporal model for the defactored real house price changes and obtain significant evidence of spatial connections, both positive and negative.
JEL Classifications: C21, C23
Key Words: Spatial and factor dependence, spatiotemporal models, positive and negative connections, house price changes.
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/wp14/bhp_Jul_19_2014.pdf

"Exponent of Crosssectional Dependence: Estimation and Inference", by Natalia Bailey, George Kapetanios and M. Hashem Pesaran, November 2013
Abstract: In this paper we provide a characterization of the degree of crosssectional dependence in a two dimensional array, [code] in terms of the rate at which the variance of the crosssectional average of the observed data varies with N. We show that under certain conditions this is equivalent to the rate at which the largest eigenvalue of the covariance matrix of [code] rises with N. We represent the degree of crosssectional dependence by , defined by the standard deviation, [code], where [code] is a simple crosssectional average of [code]. We refer to as the ‘exponent of crosssectional dependence’, and show how it can be consistently estimated for values of > 1/2. We propose bias corrected estimators, derive their asymptotic properties and consider a number of extensions. We include a detailed Monte Carlo study supporting the theoretical results. We also provide a number of empirical applications investigating the degree of interlinkages of real and financial variables in the global economy, the extent to which macroeconomic variables are interconnected across and within countries.
JEL Classifications: C21, C32
Key Words: Cross correlations, Crosssectional dependence, Crosssectional averages, Weak and strong factor models
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/wp13/BKP_CrossSectionExponent5November2013.pdf

"Theory and Practice of GVAR Modeling", by Alexander Chudik, and M. Hashem Pesaran, SSRN Research Paper Series No. 14.04, May 2014
Abstract: The Global Vector Autoregressive (GVAR) approach has proven to be a very useful approach to analyze interactions in the global macroeconomy and other data networks where both the crosssection and the time dimensions are large. This paper surveys the latest developments in the GVAR modeling, examining both the theoretical foundations of the approach and its numerous empirical applications. We provide a synthesis of existing literature and highlight areas for future research.
JEL Classifications: C32, E17.
Key Words: Global VAR, global macroeconometric modelling, global interdependencies, policy simulations.
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/wp14/cp_GVARs_8May2014.pdf

"An Exponential Class of Dynamic Binary Choice Panel Data Models with Fixed Effects", by Majid M. AlSadoon, Tong Li and M. Hashem Pesaran, CESifo Working Paper No. 4033, October 2012, revised December 2012
Abstract: This paper develops a model for dynamic binary choice panel data that allows for unobserved heterogeneity to be arbitrarily correlated with covariates. The model is of the exponential type. We derive moment conditions that enable us to eliminate the unobserved heterogeneity term and at the same time to identify the parameters of the model. We then propose GMM estimators that are consistent and asymptotically normally distributed at the rootn rate. We also study the conditional likelihood approach, which can only identify the effect of state dependence in our case. Monte Carlo experiments demonstrate the finite sample performance of our GMM estimators.
JEL Classifications: C23, C25
Key Words: Dynamic Discrete Choice, Fixed Effects, Panel Data, Initial Values, GMM, CMLE.
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/wp12/DBC102412.pdf

"A Two Stage Approach to Spatiotemporal Analysis with Strong and Weak CrossSectional Dependence", by Natalia Bailey, Sean Holly, and M. Hashem Pesaran, December 2013
Abstract: An understanding of the spatial dimension of economic and social activity requires methods that can separate out the relationship between spatial units that is due to the effect of common factors from that which is purely spatial even in an abstract sense. The same applies to the empirical analysis of networks in general. We use cross unit averages to extract common factors (viewed as a source of strong crosssectional dependence) and compare the results with the principal components approach widely used in the literature. We then apply multiple testing procedures to the defactored observations in order to determine significant bilateral correlations (signifying connections) between spatial units and compare this to an approach that just uses distance to determine units that are neighbours. We apply these methods to real house price changes at the level of Metropolitan Statistical Areas in the USA, and estimate a heterogeneous spatiotemporal model for the defactored real house price changes and obtain significant evidence of spatial connections, both positive and negative.
JEL Classifications: C21, C23
Key Words: Spatial and factor dependence, spatiotemporal models, positive and negative connections, house price changes.
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/wp13/bhp_Dec_19_2013.pdf

"Common Correlated Effects Estimation of Heterogeneous Dynamic Panel Data Models with Weakly Exogenous Regressors", by Alexander Chudik, and M. Hashem Pesaran, CESifo WP Number 4232, May 2013
Abstract: This paper extends the Common Correlated Effects (CCE) approach developed by Pesaran (2006) to heterogeneous panel data models with lagged dependent variable and/or weakly exogenous regressors. We show that the CCE mean group estimator continues to be valid but the following two conditions must be satisfied to deal with the dynamics: a sufficient number of lags of cross section averages must be included in individual equations of the panel, and the number of cross section averages must be at least as large as the number of unobserved common factors. We establish consistency rates, derive the asymptotic distribution, suggest using covariates to deal with the effects of multiple unobserved common factors, and consider jackknife and recursive demeaning bias correction procedures to mitigate the small sample time series bias. Theoretical findings are accompanied by extensive Monte Carlo experiments, which show that the proposed estimators perform well so long as the time series dimension of the panel is sufficiently large.
JEL Classifications: C31, C33
Key Words: large panels, lagged dependent variable, cross sectional dependence, coefficient heterogeneity, estimation and inference, common correlated effects, unobserved common factors.
Full Text: http://www.cesifogroup.de/ifoHome/publications/workingpapers/CESifoWP/CESifoWPdetails?wp_id=19088472

"Counterfactual Analysis in Macroeconometrics: An Empirical Investigation into the Effects of Quantitative Easin", by M. Hashem Pesaran and Ron P Smith, IZA Discussion Paper No. 6618, May 2012, revised June 2012
Abstract: This paper is concerned with ex ante and ex post counterfactual analyses in the case of macroeconometric applications where a single unit is observed before and after a given policy intervention. It distinguishes between cases where the policy change affects the model's parameters and where it does not. It is argued that for ex post policy evaluation it is important that outcomes are conditioned on ex post realized variables that are invariant to the policy change but nevertheless influence the outcomes. The effects of the control variables that are determined endogenously with the policy outcomes can be solved out for the policy evaluation exercise. An ex post policy ineffectiveness test statistic is proposed. The analysis is applied to the evaluation of the effects of the quantitative easing (QE) in the UK after March 2009. It is estimated that a 100 basis points reduction in the spread due to QE has an impact effect on output growth of about one percentage point, but the policy impact is very quickly reversed with no statistically significant effects remaining within 912 months of the policy intervention.
JEL Classifications: C18, C54, E65
Key Words: Counterfactuals, policy evaluation, macroeconomics, quantitative easing (QE), UK economic policy.
Full Text: http://www.iza.org/en/webcontent/publications/papers/viewAbstract?dp_id=6618

"Optimal Forecasts in the Presence of Structural Breaks", by M. Hashem Pesaran, Andreas Pick and Mikhail Pranovich, (2013), forthcoming in Journal of Econometrics
Abstract: This paper considers the problem of forecasting under continuous and discrete structural breaks and proposes weighting observations to obtain optimal forecasts in the MSFE sense. We derive optimal weights for one step ahead forecasts. Under continuous breaks, our approach largely recovers exponential smoothing weights. Under discrete breaks, we provide analytical expressions for optimal weights in models with a single regressor, and asymptotically valid weights for models with more than one regressor. It is shown that in these cases the optimal weight is the same across observations within a given regime and differs only across regimes. In practice, where information on structural breaks is uncertain, a forecasting procedure based on robust optimal weights is proposed. The relative performance of our proposed approach is investigated using Monte Carlo experiments and an empirical application to forecasting real GDP using the yield curve across nine industrial economies.
JEL Classifications: C22, C53
Key Words: Forecasting, structural breaks, optimal weights, robust optimal weights, exponential smoothing.
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/fp13/PPP9Feb2013.pdf
Suppliment: http://www.econ.cam.ac.uk/emeritus/mhp1/fp13/PPWebSupplement.pdf

"Signs of Impact Effects in Time Series Regression Models", by M. Hashem Pesaran and Ron P Smith, CESifo Working Paper, CAFE Research Paper No. 13.22, (2013), forthcoming in Economics Letters
Abstract: In this paper we consider the problem of interpreting the signs of the estimated coeficients in multivariate time series regressions where the regressors are correlated. Using a continuous time model, we argue that focussing on the signs of individual coeficients in such regressions could be misleading and argue in favour of allowing for the indirect effects that arise due to the historical correlations amongst the regressors. For estimation from discrete time data we show that the sign of the total impact, including the direct and indirect effects, of a regressor can be obtained using a simple regression that only includes the regressor of interest.
JEL Classifications: C1, C5
Key Words: Regression coeficients, Impact effects.
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/wp13/PSImpactSigns7October2013.pdf

"One Hundred Years of Oil Income and the Iranian Economy: A Curse or a Blessing?", by Kamiar Mohaddes, and M. Hashem Pesaran, CESifo Working Paper Series No. 4118, February 2013, forthcoming in Parvin Alizadeh and Hassan Hakimian (eds.), Iran and the Global Economy: Petro Populism, Islam and Economic Sanctions. Routledge, London.
Abstract: This paper examines the impact of oil revenues on the Iranian economy over the past hundred years, spanning the period 1908–2010. It is shown that although oil has been produced in Iran over a very long period, its importance in the Iranian economy was relatively small up until the early 1960s. It is argued that oil income has been both a blessing and a curse. Oil revenues when managed appropriately are a blessing, but their volatility (which in Iran is much higher than oil price volatility) can have adverse effects on real output, through excessively high and persistent levels of inflation. Lack of appropriate institutions and policy mechanisms which act as shock absorbers in the face of high levels of oil revenue volatility have also become a drag on real output. In order to promote growth, policies should be devised to control inflation; to serve as shock absorbers negating the adverse effects of oil revenue volatility; to reduce rent seeking activities; and to prevent excessive dependence of government finances on oil income.
JEL Classifications: E02, N15, Q32
Key Words: Oil price volatility, oil income, rent seeking, inflation, macroeconomic policy.
Available at SSRN: http://ssrn.com/abstract=2221860

"Panel Unit Root Test in the Presence of a Multifactor Error Structure", M. Hashem Pesaran, L. V. Smith, and T. Yamagata, December 2007. CWPE No. 0775, CESifo Working Papers, No. 2193, January 2008, IZA Discussion Paper No. 3254, December 2007. The University of York, Discussion Papers in Economics 08/03. Revised November 2012, forthcoming in Journal of Econometrics.
Abstract: This paper extends the crosssectionally augmented panel unit root test (CIPS) proposed by Pesaran (2007) to the case of a multifactor error structure, and proposes a new panel unit root test based on a simple average of crosssectionally augmented SarganBhargava statistics (CSB). The basic idea is to exploit information regarding the m unobserved factors that are shared by k observed time series in addition to the series under consideration. Initially, we develop the tests assuming that m0, the true number of factors is known, and show that the limit distribution of the tests does not depend on any nuisance parameters, so long asSmall sample properties of the tests are investigated by Monte Carlo experiments and are shown to be satisfactory. Particularly, the proposed CIPS and CSB tests have the correct size for all combinations of the cross section (N) and time series (T) dimensions considered. The power of both tests rise with N and T, although the CSB test performs better than the CIPS test for smaller sample sizes. The various testing procedures are illustrated with empirical applications to real interest rates and real equity prices across countries.
Key Words: Panel unit root tests, Cross section dependence, Multifactor error structure, Fisher inflation parity, Real equity prices.
JEL Classifications: C12, C15, C22, C23
Full Text: http://authors.elsevier.com/sd/article/S0304407613000353
Supplement: http://www.econ.cam.ac.uk/emeritus/mhp1/fp13/20121022PSY_Supplement(MSNo2009229).pdf
Gauss Codes: http://www.econ.cam.ac.uk/emeritus/mhp1/fp13/Gauss_Code.zip

"Testing CAPM with a Large Number of Assets", by M. Hashem Pesaran and Takashi Yamagata, CWPE Working Paper No. 1210, IZA Discussion Paper No. 6469, under revision, February 2012, under revision
Abstract: This paper is concerned with testing the time series implications of the capital asset pricing model (CAPM) due to Sharpe (1964) and Lintner (1965), when the number of securities, N, is large relative to the time dimension, T, of the return series. In the case of crosssectionally correlated errors, using a threshold estimator of the average squares of pairwise error correlations a test is proposed and is shown to be valid even if N is much larger than T. Monte Carlo evidence show that the proposed test works well in small samples. The test is then applied to all securities in the S&P 500 index with 60 months of return data at the end of each month over the period September 1989September 2011. Statistically significant evidence against SharpeLintner CAPM is found mainly during the recent financial crisis. Furthermore, a strong negative correlation is found between a twelvemonth moving average pvalues of the test and the returns of long/short equity strategies relative to the return on S&P 500 over the period December 2006 to September 2011, suggesting that abnormal profits are earned during episodes of market inefficiencies.
JEL Classifications: C12, C15, C23, G11, G12
Key Words: CAPM, Testing for alpha, Market efficiency, Long/short equity returns, Large panels, Weak and strong crosssectional dependence.
Full Text: http://www.iza.org/en/webcontent/publications/papers/viewAbstract?dp_id=6469

"An Empirical Growth Model for Major Oil Exporters", by Hadi Salehi Esfahani, Kamiar Mohaddes and M. Hashem Pesaran, (2012), forthcoming in Journal of Applied Econometrics
Abstract: This paper develops a longrun output relation for a major oil exporting economy where the oil income to output ratio remains sufficiently high over a prolonged period. It extends the stochastic growth model developed in Binder and Pesaran (1999) by including oil exports as an additional factor in the capital accumulation process. The paper distinguishes between the two cases where the growth of oil income, g0, is less than the natural growth rate (the sum of the population growth, n, and the growth of technical progress, g), and when g0 > g+n. Under the former, the effects of oil income on the economy's steady growth rate will vanish eventually, whilst under the latter, oil income enters the longrun output equation with a coefficient which is equal to the share of capital if it is further assumed that the underlying production technology can be represented by a CobbDouglas production function. The longrun theory is tested using quarterly data on nine major oil economies. Overall, the test results support the longrun theory, with the existence of longrun relations between real output, foreign output and real oil income established for six of the nine economies considered.
JEL Classifications: C32, C53, E17, F43, F47, Q32
Key Words: Growth models, longrun and errorcorrecting relations, major oil exporters, OPEC member countries, oil exports and foreign output shocks.
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/fp12/EMPJAE4June2012.pdf
Data: /peoplefiles/cto/km418/EMP_Data.zip

"Aggregation in Large Dynamic Panels", by M. Hashem Pesaran, Alexander Chudik, (2012), forthcoming in Journal of Econometrics
Abstract: This paper investigates the problem of aggregation in the case of large linear dynamic panels, where each micro unit is potentially related to all other micro units, and where micro innovations are allowed to be cross sectionally dependent. Following Pesaran (2003), an optimal aggregate function is derived and used (i) to establish conditions under which Granger's (1980) conjecture regarding the long memory properties of aggregate variables from 'a very large scale dynamic, econometric model' holds, and (ii) to show which distributional features of micro parameters can be identified from the aggregate model. The paper also derives impulse response functions for the aggregate variables, distinguishing between the effects of macro and aggregated idiosyncratic shocks. Some of the findings of the paper are illustrated by Monte Carlo experiments. The paper also contains an empirical application to consumer price inflation in Germany, France and Italy, and reexamines the extent to which 'observed' inflation persistence at the aggregate level is due to aggregation and/or common unobserved factors. Our findings suggest that dynamic heterogeneity as well as persistent common factors are needed for explaining the observed persistence of the aggregate inflation.
JEL Classifications: C43, E31
Key Words: Aggregation, Large Dynamic Panels, Long Memory, Weak and Strong Cross Section Dependence, VAR Models, Impulse Responses, Factor Models, Inflation Persistence.
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/fp12/Pesaran&ChudikAggregation1March2012.pdf

"Robust Standard Errors in Transformed Likelihood Estimation of Dynamic Panel Data Models", by Kazuhiko Hayakawa and M. Hashem Pesaran, CWPE Working Paper No. 1224, IZA Discussion Paper 6583, Cesifo Working Paper No.3850, April 2012, revised April 2012
Abstract: This paper extends the transformed maximum likelihood approach for estimation of dynamic panel data models by Hsiao, Pesaran, and Tahmiscioglu (2002) to the case where the errors are crosssectionally heteroskedastic. This extension is not trivial due to the incidental parameters problem that arises, and its implications for estimation and inference. We approach the problem by working with a misspecified homoskedastic model. It is shown that the transformed maximum likelihood estimator continues to be consistent even in the presence of crosssectional heteroskedasticity. We also obtain standard errors that are robust to crosssectional heteroskedasticity of unknown form. By means of Monte Carlo simulation, we investigate the finite sample behavior of the transformed maximum likelihood estimator and compare it with various GMM estimators proposed in the literature. Simulation results reveal that, in terms of median absolute errors and accuracy of inference, the transformed likelihood estimator outperforms the GMM estimators in almost all cases.
JEL Classifications: C12, C13, C23
Key Words: Dynamic Panels, Crosssectional heteroskedasticity, Monte Carlo simulation, GMM estimation.
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/wp12/Hayakawa_Pesaran_robustML_27_April_2012.pdf
Matlab Code: http://www.econ.cam.ac.uk/emeritus/mhp1/wp12/MatlabcodeanddataforTransMLHayakawaandPesaran2012.zip

"Signs of Impact Effects in Time Series Regression Models", by M. Hashem Pesaran and Ron P Smith, CESifo Working Paper, CAFE Research Paper No. 13.22 , October 2013
Abstract: In this paper we consider the problem of interpreting the signs of the estimated coeficients in multivariate time series regressions where the regressors are correlated. Using a continuous time model, we argue that focussing on the signs of individual coeficients in such regressions could be misleading and argue in favour of allowing for the indirect effects that arise due to the historical correlations amongst the regressors. For estimation from discrete time data we show that the sign of the total impact, including the direct and indirect effects, of a regressor can be obtained using a simple regression that only includes the regressor of interest.
JEL Classifications: C1, C5
Key Words: Regression coeficients, Impact effects.
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/wp13/PSImpactSigns7October2013.pdf

"Large Panel Data Models with CrossSectional Dependence: A Survey", by Alexander Chudik, and M. Hashem Pesaran, CESifo WP Number 4371, August 2013
Abstract: This paper provides an overview of the recent literature on estimation and inference in large panel data models with crosssectional dependence. It reviews panel data models with strictly exogenous regressors as well as dynamic models with weakly exogenous regressors. The paper begins with a review of the concepts of weak and strong crosssectional dependence, and discusses the exponent of crosssectional dependence that characterizes the different degrees of crosssectional dependence. It considers a number of alternative estimators for static and dynamic panel data models, distinguishing between factor and spatial models of crosssectional dependence. The paper also provides an overview of tests of independence and weak crosssectional dependence.
JEL Classifications: C31, C33
Key Words: Large panels, weak and strong crosssectional dependence, factor structure, spatial dependence, tests of crosssectional dependence.
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/wp13/ChudikPesaranSurevyCSD13August2013.pdf

"One Hundred Years of Oil Income and the Iranian Economy: A Curse or a Blessing?", by Kamiar Mohaddes, and M. Hashem Pesaran, CESifo Working Paper Series No. 4118, December 2012, revised February 2013.
Abstract: This paper examines the impact of oil revenues on the Iranian economy over the past hundred years, spanning the period 1908–2010. It is shown that although oil has been produced in Iran over a very long period, its importance in the Iranian economy was relatively small up until the early 1960s. It is argued that oil income has been both a blessing and a curse. Oil revenues when managed appropriately are a blessing, but their volatility (which in Iran is much higher than oil price volatility) can have adverse effects on real output, through excessively high and persistent levels of inflation. Lack of appropriate institutions and policy mechanisms which act as shock absorbers in the face of high levels of oil revenue volatility have also become a drag on real output. In order to promote growth, policies should be devised to control inflation; to serve as shock absorbers negating the adverse effects of oil revenue volatility; to reduce rent seeking activities; and to prevent excessive dependence of government finances on oil income.
JEL Classifications: E02, N15, Q32
Key Words: Oil price volatility, oil income, rent seeking, inflation, macroeconomic policy.
Available at SSRN: http://ssrn.com/abstract=2221860

"Supply, Demand and Monetary Policy Shocks in a MultiCountry New Keynesian Model", by Stephane Dees, M. Hashem Pesaran, Ron P. Smith and L. Vanessa Smith, CESifo Working Papers No. 3081, June 2011, revised October 2012
Abstract: This paper estimates and solves a multicountry version of the standard New Keynesian, MCNK, model. Modelling a large number of countries requires a range of methodological innovations. Each country has a Phillips curve determining inflation, an IS curve determining output, a Taylor Rule determining interest rates, and a real effective exchange rate equation. All variables are measured as deviations from their steady states, estimated as longhorizon forecasts from a reducedform cointegrating global VAR. The rational expectations model is estimated for 33 countries, 1980Q12006Q4, by inequality constrained IV, using lagged and contemporaneous foreign variables as instruments, subject to NK theoretical restrictions. The MCNK model is then solved to provide estimates of identified supply, demand and monetary policy shocks. Within a country supply, demand and monetary policy shocks are orthogonal, though shocks of the same type (e.g. supply shocks in different countries) can be correlated. We present impulse response functions and variance decompositions allowing for both direct channels of international transmission through regression coefficients and indirect channels through error spillover effects. Bootstrapped error bands are also provided for the cross country responses of a shock to the US monetary policy.
JEL Classifications: C32, E17, F37, F42
Key Words: Global VAR (GVAR), Multicountry New Keynesian (MCNK) models, supply shocks, demand shocks, monetary policy shocks
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/wp11/DPSS_MCNKJune2011.pdf
Supplement: http://www.econ.cam.ac.uk/emeritus/mhp1/wp11/DPSS_MCNK_Supplement_June2011.pdf
Readme Data: http://www.econ.cam.ac.uk/emeritus/mhp1/wp10/ReadmeDataDPSS(2010).pdf
Transformed Data: http://www.econ.cam.ac.uk/emeritus/mhp1/wp10/TransformedData(1979Q12006Q4).zip
Source Data: http://www.econ.cam.ac.uk/emeritus/mhp1/wp10/SourceData(1979Q12006Q4).zip

"Counterfactual Analysis in Macroeconometrics: An Empirical Investigation into the Effects of Quantitative Easin", by M. Hashem Pesaran and Ron P Smith, May 2012
Abstract: This paper is concerned with ex ante and ex post counterfactual analyses in the case of macroeconometric applications where a single unit is observed before and after a given policy intervention. It distinguishes between cases where the policy change affects the model's parameters and where it does not. It is argued that for ex post policy evaluation it is important that outcomes are conditioned on ex post realized variables that are invariant to the policy change but nevertheless influence the outcomes. The effects of the control variables that are determined endogenously with the policy outcomes can be solved out for the policy evaluation exercise. An ex post policy ineffectiveness test statistic is proposed. The analysis is applied to the evaluation of the effects of the quantitative easing (QE) in the UK after March 2009. It is estimated that a 100 basis points reduction in the spread due to QE has an impact effect on output growth of about one percentage point, but the policy impact is very quickly reversed with no statistically significant effects remaining within 912 months of the policy intervention.
JEL Classifications: C18, C54, E65
Key Words: Counterfactuals, policy evaluation, macroeconomics, quantitative easing (QE), UK economic policy.
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/wp12/PSonCF16May2012.pdf

"One Hundred Years of Oil Income and the Iranian Economy: A Curse or a Blessing?", by Kamiar Mohaddes, and M. Hashem Pesaran, December 2012
Abstract: This paper examines the impact of oil revenues on the Iranian economy over the past hundred years, spanning the period 1908–2010. It is shown that although oil has been produced in Iran over a very long period, its importance in the Iranian economy was relatively small up until the early 1960s. It is argued that oil income has been both a blessing and a curse. Oil revenues when managed appropriately are a blessing, but their volatility (which in Iran is much higher than oil price volatility) can have adverse effects on real output, through excessively high and persistent levels of inflation. Lack of appropriate institutions and policy mechanisms which act as shock absorbers in the face of high levels of oil revenue volatility have also become a drag on real output. In order to promote growth, policies should be devised to control inflation; to serve as shock absorbers negating the adverse effects of oil revenue volatility; to reduce rent seeking activities; and to prevent excessive dependence of government finances on oil income.
JEL Classifications: E02, N15, Q32
Key Words: Oil price volatility, oil income, rent seeking, inflation, macroeconomic policy.
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/wp12/DBC102412.pdf

"Testing Weak CrossSectional Dependence in Large Panels", by M. Hashem Pesaran, January 2012, Revised January 2013
Abstract: This paper considers testing the hypothesis that errors in a panel data model are weakly cross sectionally dependent, using the exponent of crosssectional dependence , introduced recently in Bailey, Kapetanios and Pesaran (2012). It is shown that the implicit null of the CD test depends on the relative expansion rates of N and T. When T = O , for some , then the implicit null of the CD test is given by , which gives , when N and T tend to infinity at the same rate such that T/N , with being a finite positive constant. It is argued that in the case of large N panels, the null of weak dependence is more appropriate than the null of independence which could be quite restrictive for large panels. Using Monte Carlo experiments, it is shown that the CD test has the correct size for values of in the range [0, 1/4], for all combinations of N and T, and irrespective of whether the panel contains lagged values of the dependent variables, so long as there are no major asymmetries in the error distribution.
JEL Classifications: C12, C13, C3
Key Words: Exponent of crosssectional dependence, Diagnostic tests, Panel data models, Dynamic heterogenous panels.
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/wp13/PesaranWCDTest11Jan2013.pdf

"Econometric Analysis of High Dimensional VARs Featuring a Dominant Unit", by M. Hashem Pesaran and Alexander Chudik, (2011), forthcoming in the Econometrics Review.
Abstract: This paper extends the analysis of infinite dimensional vector autoregressive (IVAR) models proposed in Chudik and Pesaran (2011) to the case where one of the variables or the cross section units in the IVAR model is dominant or pervasive. It is an important extension from empirical as well theoretical perspectives. In the theory of networks a dominant unit is the centre node of a star network and arises as an efficient outcome of a distancebased utility model. Empirically, the extension poses a number of technical challenges that goes well beyond the analysis of IVAR models provided in Chudik and Pesaran. This is because the dominant unit influences the rest of the variables in the IVAR model both directly and indirectly, and its effects do not vanish as the dimension of the model (N) tends to infinity. The dominant unit acts as a dynamic factor in the regressions of the nondominant units and yields an infinite order distributed lag relationship between the two types of units. Despite this it is shown that the effects of the dominant unit as well as those of the neighborhood units can be consistently estimated by running augmented least squares regressions that include distributed lag functions of the dominant unit and its neighbors (if any). The asymptotic distribution of the estimators is derived and their small sample properties investigated by means of Monte Carlo experiments.
JEL Classifications: C10, C33, C51
Key Words: IVAR Models, Dominant Units, Star Networks, Large Panels, Weak and Strong Cross Section Dependence, Factor Models, Spatial Models.
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/fp11/PesaranChudik_IVARD_1 April 11.pdf

"Common Correlated Effects Estimation of Heterogeneous Dynamic Panel Data Models with Weakly Exogenous Regressors", by Alexander Chudik, and M. Hashem Pesaran, April 2013
Abstract: This paper extends the Common Correlated Effects (CCE) approach developed by Pesaran (2006) to heterogeneous panel data models with lagged dependent variable and/or weakly exogenous regressors. We show that the CCE mean group estimator continues to be valid but the following two conditions must be satisfied to deal with the dynamics: a sufficient number of lags of cross section averages must be included in individual equations of the panel, and the number of cross section averages must be at least as large as the number of unobserved common factors. We establish consistency rates, derive the asymptotic distribution, suggest using covariates to deal with the effects of multiple unobserved common factors, and consider jackknife and recursive demeaning bias correction procedures to mitigate the small sample time series bias. Theoretical findings are accompanied by extensive Monte Carlo experiments, which show that the proposed estimators perform well so long as the time series dimension of the panel is sufficiently large.
JEL Classifications: C31, C33
Key Words: Large panels, lagged dependent variable, cross sectional dependence, coefficient heterogeneity, estimation and inference, common correlated effects, unobserved common factors.
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/wp13/CP_DynamicCCE_25 Apr2013.pdf

"Panel Unit Root Test in the Presence of a Multifactor Error Structure", M. Hashem Pesaran, L. V. Smith, and T. Yamagata, (2013), forthcoming in Journal of Econometrics, Revised 2012
Abstract: This paper extends the crosssectionally augmented panel unit root test (CIPS) proposed by Pesaran (2007) to the case of a multifactor error structure, and proposes a new panel unit root test based on a simple average of crosssectionally augmented SarganBhargava statistics (CSB). The basic idea is to exploit information regarding the m unobserved factors that are shared by k observed time series in addition to the series under consideration. Initially, we develop the tests assuming that m0, the true number of factors is known, and show that the limit distribution of the tests does not depend on any nuisance parameters, so long asSmall sample properties of the tests are investigated by Monte Carlo experiments and are shown to be satisfactory. Particularly, the proposed CIPS and CSB tests have the correct size for all combinations of the cross section (N) and time series (T) dimensions considered. The power of both tests rise with N and T, although the CSB test performs better than the CIPS test for smaller sample sizes. The various testing procedures are illustrated with empirical applications to real interest rates and real equity prices across countries.
Key Words: Panel Unit Root Tests, Cross Section Dependence, Multifactor Error Structure, Fisher Inflation Parity, Real Equity Prices.
JEL Classifications: C12, C15, C22, C23
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/fp13/PanelUnitPSY(MSNo2009229_4).pdf
Supplement: http://www.econ.cam.ac.uk/emeritus/mhp1/fp13/20121022PSY_Supplement(MSNo2009229).pdf
Gauss Codes: http://www.econ.cam.ac.uk/emeritus/mhp1/fp13/Gauss_Code.zip

"A Panel Unit Root Test in the Presence of a Multifactor Error Structure", M. Hashem Pesaran, L. V. Smith, and T. Yamagata. December, 2007, Revised September 2009
Abstract: This paper extends the cross sectionally augmented panel unit root test proposed by Pesaran (2007) to the case of a multifactor error structure. The basic idea is to exploit information regarding the m unobserved factors that are shared by k other time series in addition to the variable under consideration. Initially we develop a test assuming that , the true number of factors is known, and show that the limit distribution of the test does not depend on any nuisance parameters, so long as Small sample properties of the test are investigated by Monte Carlo experiments and shown to be satisfactory. Particularly, in contrast to other existing panel unit root tests, our test has correct size and reasonable power for the case with an intercept and a linear trend as well as with an intercept only, for all combinations of cross section and time series dimensions. An illustrative application is also provided where the proposed panel unit root test is applied to Fisher’s inflation parity and real equity prices.
Key Words: Panel Unit Root Tests, Cross Section Dependence, Multifactor Residual Structure, Fisher Inflation Parity, Real Equity Prices..
JEL Classifications: C12, C15, C22, C23
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/wp09/PSY_16Sept2009_Vanessa.pdf
Gauss Codes and Supplemental Critical Value Tables: http://www.econ.cam.ac.uk/emeritus/mhp1/wp08/CIPSM.zip

"Business Cycle Effects of Credit and Technology Shocks in a DSGE Model with Firm Default", by M. Hashem Pesaran and TengTeng Xu, October 2011
Abstract: This paper proposes a theoretical framework to analyze the impacts of credit and technology shocks on business cycle dynamics, where firms rely on banks and households for capital financing. Firms are identical ex ante but differ ex post due to different realizations of firm specific technology shocks, possibly leading to default by some firms. The paper advances a new modelling approach for the analysis of financial intermediation and firm defaults that takes account of the financial implications of such defaults for both households and banks. Results from a calibrated version of the model highlights the role of financial institutions in the transmission of credit and technology shocks to the real economy. A positive credit shock, defined as a rise in the loan to deposit ratio, increases output, consumption, hours and productivity, and reduces the spread between loan and deposit rates. The effects of the credit shock tend to be highly persistent even without price rigidities and habit persistence in consumption behaviour.
JEL Classifications: E32, E44, G21.
Key Words: Bank Credit, Financial Intermediation, Firm Heterogeneity and Defaults, Interest Rate Spread, Real Financial Linkages.
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/wp11/MacroCredit_ 6Oct2011_WorkingPaper.pdf
Supplement: http://www.econ.cam.ac.uk/emeritus/mhp1/wp11/MacroCredit_ 5Oct2011_Supplement.pdf

"Optimal Forecasts in the Presence of Structural Breaks", by M. Hashem Pesaran, Andreas Pick and Mikhail Pranovich, October 2011, Revised December 2011
Abstract: This paper considers the problem of forecasting under continuous and discrete structural breaks and proposes weighting observations to obtain optimal forecasts in the MSFE sense. We derive optimal weights for continuous and discrete break processes. Under continuous breaks, our approach recovers exponential smoothing weights. Under discrete breaks, we provide analytical expressions for the weights in models with a single regressor and asympotically for larger models. It is shown that in these cases the value of the optimal weight is the same across observations within a given regime and differs only across regimes. In practice, where information on structural breaks is uncertain a forecasting procedure based on robust weights is proposed. Monte Carlo experiments and an empirical application to the predictive power of the yield curve analyze the performance of our approach relative to other forecasting methods.
JEL Classifications: C22, C53
Key Words: Forecasting, structural breaks, optimal weights, robust weights, exponential smoothing.
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/wp11/PPP9Dec2011.pdf

"On Identification of Bayesian DSGE Models", by Gary Koop, M. Hashem Pesaran and Ron P. Smith, March 2011, Revised August 2012
Abstract: This paper is concerned with identification of dynamic stochastic general equilibrium (DSGE) models from a Bayesian perspective, and proposes two Bayesian indicators. The first indicator follows a suggestion by Poirier of comparing the posterior density of the parameter of interest with the posterior expectation of its prior conditional on the remaining parameters, as opposed to comparing the posterior distribution to its prior as is usually done.
The second indicator examines the rate at which the posterior precision of the parameter gets updated with the sample size, using simulated data. For identified parameters the posterior precision increases at rate T. We show that for parameters that are either unidentified or are weakly identified the posterior precision may be updated but its rate of update will be slower than T. We use empirical examples to demonstrate that these methods are useful in practice.
JEL Classifications: C11, C15, E17
Key Words: Bayesian identification, weak identification, DSGE models, posterior updating.
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/wp12/KPS6August12.pdf

"Testing Weak CrossSectional Dependence in Large Panels", by M. Hashem Pesaran, January 2012
Abstract: This paper considers testing the hypothesis that errors in a panel data model are weakly cross sectionally dependent, using the exponent of crosssectional dependence , introduced recently in Bailey, Kapetanios and Pesaran (2012). It is shown that the implicit null of the CD test depends on the relative expansion rates of N and T. When T = O , for some , then the implicit null of the CD test is given by , which gives , when N and T tend to infinity at the same rate such that T/N , with being a finite positive constant. It is argued that in the case of large N panels, the null of weak dependence is more appropriate than the null of independence which could be quite restrictive for large panels. Using Monte Carlo experiments, it is shown that the CD test has the correct size for values of in the range [0, 1/4], for all combinations of N and T, and irrespective of whether the panel contains lagged values of the dependent variables, so long as there are no major asymmetries in the error distribution.
JEL Classifications: C12, C13, C3
Key Words: Exponent of crosssectional dependence, Diagnostic tests, Panel data models, Dynamic heterogenous panels.
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/wp12/PesaranWCDTest30Jan2012.pdf

"On Identification of Bayesian DSGE Models", by Gary Koop, M. Hashem Pesaran and Ron P. Smith, March 2011, Revised September 2011
Abstract: In recent years there has been increasing concern about the identi…fication of parameters in dynamic stochastic general equilibrium (DSGE) models. Given the structure of DSGE models it may be difficult to determine whether a parameter is identified. For the researcher using Bayesian methods, a lack of identification may not be evident since the posterior of a parameter of interest may differ from its prior even if the parameter is unidentified. We show that this can be the case even if the priors assumed on the structural parameters are independent. We suggest two Bayesian identification indicators that do not suffer from this difficulty and are relatively easy to compute. The first applies to DSGE models where the parameters can be partitioned into those that are known to be identified and the rest where it is not known whether they are identified. In such cases the marginal posterior of an unidentified parameter will equal the posterior expectation of the prior for that parameter conditional on the identified parameters. The second indicator is more generally applicable and considers the rate at which the posterior precision gets updated as the sample size (T) is increased. For identified parameters the posterior precision rises with T, whilst for an unidentified parameter its posterior precision may be updated but its rate of update will be slower than T. This result assumes that the identified parameters are consistent, but similar differential rates of updates for identified and unidentified parameters can be established in the case of weak (or super) consistent estimators. These results are illustrated by means of simple DSGE models.
JEL Classifications: C11, C15, E17
Key Words: Bayesian identification, DSGE models, posterior updating, New Keynesian Phillips Curve.
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/wp11/KPS30Sept11.pdf

"Oil Exports and the Iranian Economy", by Hadi Salehi Esfahani, Kamiar Mohaddes and M. Hashem Pesaran, April 2012
Abstract: This paper presents an errorcorrecting macroeconometric model for the Iranian economy estimated using a new quarterly data set over the period 1979Q12006Q4. It builds on a recent paper by the authors, Esfahani et al. (2012), which develops a theoretical longrun growth model for major oil exporting economies. The core variables included in this paper are real output, real money balances, inflation, exchange rate, oil exports, and foreign real output, although the role of investment and consumption are also analyzed in a submodel. The paper finds clear evidence for the existence of two longrun relations: an output equation as predicted by the theory and a standard real money demand equation with inflation acting as a proxy for the (missing) market interest rate. The results show that real output in the long run is influenced by oil exports and foreign output. However, it is also found that inflaation has a signifiicant negative longrun effect on real GDP, which is suggestive of economic inefficiencies and is matched by a negative association between inflation and the investmentoutput ratio. Finally, the results of impulse responses show that the Iranian economy adjusts quite quickly to the shocks in foreign output and oil exports, which could be partly due to the relatively underdeveloped nature of Iran’s financial markets.
JEL Classifications: C32, C53, E17, F43, F47, Q32
Key Words: Growth models, longrun relations, oil exporters, Iranian economy, oil price and foreign output shocks, and errorcorrecting relations.
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/wp12/Iran_VARX_18 April 12.pdf

"Oil Exports and the Iranian Economy", by Hadi Salehi Esfahani, Kamiar Mohaddes, and M. Hashem Pesaran October, 2009
Abstract: This paper develops a long run growth model for a major oil exporting economy and derives conditions under which oil revenues are likely to have a lasting impact. This approach contrasts with the standard literature on the "Dutch disease" and the "resource curse", which primarily focus on short run implications of a temporary resource discovery. Under certain regularity conditions and assuming a Cobb Douglas production function, it is shown that (log) oil exports enter the long run output equation with a coeficient equal to the share of capital. The long run theory is tested using a new quarterly data set on the Iranain economy over the period 1979Q12006Q4. Building an error correction specification in real output, real money balances, inflation, real exchange rate, oil exports, and foreign real output, the paper finds clear evidence for two long run relations: an output equation as predicted by the theory and a standard real money demand equation with inflation acting as a proxy for the (missing) market interest rate. Real output in the long run is shaped by oil exports through their impact on capital accumulation, and the foreign output as the main channel of technological transfer. The results also show a significant negative long run association between inflation and real GDP, which is suggestive of economic ineficiencies. Once the effects of oil exports are taken into account, the estimates support output growth convergence between Iran and the rest of the world. We also find that the Iranian economy adjusts quite quickly to the shocks in foreign output and oil exports, which could be partly due to the relatively underdeveloped nature of Iran’s financial markets.
JEL Classifications: Growth models, long run relations, Iranian economy, oil price and foreign output shocks, and error correcting relations.
Key Words: C32, C53, E17, F43, F47, Q32.
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/wp09/Iran_VARX_08Oct09.pdf
Data: http://www.econ.cam.ac.uk/teach/mohaddes/Iran_VARX_Data.zip

"On the Interpretation of Panel Unit Root Tests", by M. Hashem Pesaran, September 2011
Abstract: Applications of panel unit root tests have become commonplace in empirical economics, yet there are ambiguities as how best to interpret the test results. This note clarifies that rejection of the panel unit root hypothesis should be interpreted as evidence that a statistically significant proportion of the units are stationary. Accordingly, in the event of a rejection, and in applications where the time dimension of the panel is relatively large, it recommends the test outcome to be augmented with an estimate of the proportion of the crosssection units for which the individual unit root tests are rejected. The economic importance of the rejection can be measured by the magnitude of this proportion.
JEL Classifications: C12, C33, C52
Key Words: Unit Root tests, Panels, Statistical Significance.
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/wp11/InterpretationPanelUnitSeptember2011.pdf

"Aggregation in Large Dynamic Panels", by M. Hashem Pesaran, Alexander Chudik, January 2011, Revised November 2011
Abstract: This paper investigates the problem of aggregation in the case of large linear dynamic panels, where each micro unit is potentially related to all other micro units, and where micro innovations are allowed to be cross sectionally dependent. Following Pesaran (2003), an optimal aggregate function is derived and used (i) to establish conditions under which Granger’s (1980) conjecture regarding the long memory properties of aggregate variables from ‘a very large scale dynamic, econometric model’holds, and (ii) to show which distributional features of micro parameters can be identified from the aggregate model. The paper also derives impulse response functions for the aggregate variables, distinquishing between the effects of macro and aggregated idiosyncratic shocks. Some of the findings of the paper are illustrated by Monte Carlo experiments. The paper also contains an empirical application to consumer price inflation in Germany, France and Italy, and reexamines the extent to which ‘observed’inflation persistence at the aggregate level is due to aggregation and/or common unobserved factors. Our findings suggest that dynamic heterogeneity as well as persistent common factors are needed for explaining the observed persistence of the aggregate inflation.
JEL Classifications: C43, E31
Key Words: Aggregation, Large Dynamic Panels, Long Memory,Weak and Strong Cross Section Dependence, VAR Models, Impulse Responses, Factor Models, Inflation Persistenc.
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/wp11/PesaranChudik_Aggregation_16_Nov_2011.pdf

"Beyond the DSGE Straitjacket, by M. Hashem Pesaran and Ron P. Smith, May 2011
Abstract: Academic macroeconomics and the research department of central banks have come to be dominated by Dynamic, Stochastic, General Equilibrium (DSGE) models based on microfoundations of optimising representative agents with rational expectations. We argue that the dominance of this particular sort of DSGE and the resistance of some in the profession to alternatives has become a straitjacket that restricts empirical and theoretical experimentation and inhibits innovation and that the profession should embrace a more flexible approach to macroeconometric modelling. We describe one possible approach.
JEL Classifications: C100, E100
Key Words: macroeconometric models, DSGE, VARs, long run theory.
Full Text: http://papers.ssrn.com/sol3/papers.cfm?abstract_id=1844075

"China's Emergence in the World Economy and Business Cycles in Latin America", by Ambrogio CesaBianchi, M. Hashem Pesaran, Alessandro Rebucci and TengTeng Xu, July 2011
Abstract: The international business cycle is very important for Latin America's economic performance as the recent global crisis vividly illustrated. This paper investigates how changes in trade linkages between China, Latin America, and the rest of the world have altered the transmission mechanism of international business cycles to Latin America. Evidence based on a Global Vector Autoregressive (GVAR) model for 5 large Latin American economies and all major advanced and emerging economies of the world shows that the longterm impact of a China GDP shock on the typical Latin American economy has increased by three times since mid1990s. At the same time, the longterm impact of a US GDP shock has halved, while the transmission of shocks to Latin America and the rest of emerging Asia (excluding China and India) GDP has not undergone any signicant change. Contrary to common wisdom, we find that these changes owe more to the changed impact of China on Latin America's traditional and largest trading partners than to increased direct bilateral trade linkages boosted by the decadelong commodity price boom. These findings help to explain why Latin America did so well during the global crisis, but point to the risks associated with a deceleration in China's economic growth in the future for both Latin America and the rest of the world economy. The evidence reported also suggests that the emergence of China as an important source of world growth might be the driver of the so called "decoupling" of emerging markets business cycle from that of advanced economies reported in the existing literature.
JEL Classifications: C32, F44, E32, O54
Key Words: China, GVAR, Great Recession, Emerging Markets, International Business Cycle, Latin America, Trade linkages.
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/wp11/CPRX_ECONOMIA_July27.pdf

"Beyond the DSGE straitjacket", by M. Hashem Pesaran and Ron P. Smith, April 2011
Abstract: Academic macroeconomics and the research department of central banks have come to be dominated by Dynamic, Stochastic, General Equilibrium (DSGE) models based on microfoundations of optimising representative agents with rational expectations. We argue that the dominance of this particular sort of DSGE and the resistance of some in the profession to alternatives has become a straitjacket that restricts empirical and theoretical experimentation and inhibits innovation and that the profession should embrace a more flexible approach to macroeconometric modelling. We describe one possible approach.
JEL Classifications: C1, E1
Key Words: Macroeconometric models, DSGE, VARs, long run theory
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/wp11/PesaranandSmith2011SSRNid1844075.pdf

"Econometric Analysis of High Dimensional VARs Featuring a Dominant Unit", by M. Hashem Pesaran and Alexander Chudik. March, 2010
Abstract: This paper extends the analysis of infinite dimensional vector autoregressive models (IVAR) proposed in Chudik and Pesaran (2010) to the case where one of the variables or the cross section units in the IVAR model is dominant or pervasive. This extension is not straightforward and involves several technical difficulties. The dominant unit influences the rest of the variables in the IVAR model both directly and indirectly, and its effects do not vanish even as the dimension of the model (N) tends to infinity. The dominant unit acts as a dynamic factor in the regressions of the nondominant units and yields an infinite order distributed lag relationship between the two types of units. Despite this it is shown that the effects of the dominant unit as well as those of the neighborhood units can be consistently estimated by running augmented least squares regressions that include distributed lag functions of the dominant unit. The asymptotic distribution of the estimators is derived and their small sample properties investigated by means of Monte Carlo experiments.
JEL Classifications: C10, C33, C51
Key Words: IVAR Models, Dominant Units, Large Panels, Weak and Strong Cross Section Dependence, Factor Models
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/wp10/PesaranChudik_IVARD_19Mar10.pdf

"Supply, Demand and Monetary Policy Shocks in a MultiCountry New Keynesian Model", by Stephane Dees, M. Hashem Pesaran, L. Vanessa Smith and Ron P. Smith. May, 2010
Abstract: This paper estimates and solves a multicountry version of the standard DSGE New Keynesian (NK) model. The countryspecific models include a Phillips curve determining inflation, an IS curve determining output, a Taylor Rule determining interest rates, and a real effective exchange rate equation. The IS equation includes a real exchange rate variable and a countryspecific foreign output variable to capture direct intercountry linkages. In accord with the theory all variables are measured as deviations from their steady states, which are estimated as longhorizon forecasts from a reducedform cointegrating global vector autoregression. The resulting rational expectations model is then estimated for 33 countries on data for 1980Q1 2006Q4, by inequality constrained IV, using lagged and contemporaneous foreign variables as instruments, subject to the restrictions implied by the NK theory. The multicountry DSGE NK model is then solved to provide estimates of identified supply, demand and monetary policy shocks. Following the literature, we assume that the within country supply, demand and monetary policy shocks are orthogonal, though shocks of the same type (e.g. supply shocks in different countries) can be correlated. We discuss estimation of impulse response functions and variance decompositions in such large systems, and present estimates allowing for both direct channels of international transmission through regression coefficients and indirect channels through error spillover effects. Bootstrapped error bands are also provided for the cross country responses of a shock to the US monetary policy.
JEL Classifications: C32, E17, F37, F42
Key Words: Global VAR (GVAR), New Keynesian DSGE models, supply shocks, demand shocks, monetary policy shocks.
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/wp10/DeesPesaranSmithSmithMCNK28May10.pdf
Supplement: http://www.econ.cam.ac.uk/emeritus/mhp1/wp10/DPSS_MCNK_Supplement_27July10.pdf
Readme Data: http://www.econ.cam.ac.uk/emeritus/mhp1/wp10/ReadmeDataDPSS(2010).pdf
Transformed Data: http://www.econ.cam.ac.uk/emeritus/mhp1/wp10/TransformedData(1979Q12006Q4).zip
Source Data: http://www.econ.cam.ac.uk/emeritus/mhp1/wp10/SourceData(1979Q12006Q4).zip

"Diagnostic Tests of Cross Section Independence for Limited Dependent Variable Panel Data Models", by Cheng Hsiao, M. Hashem Pesaran and Andreas Pick April, 2007, Revised July 2010
Abstract: This paper considers the problem of testing for cross section independence in limited dependent variable panel data models. It derives a Lagrangian multiplier (LM) test and shows that in terms of generalized residuals of Gourieroux, Monfort, Renault and Trognon (1987) it reduces to the LM test of Breusch and Pagan (1980). Due to the tendency of the LM test to overreject in panels with large N (cross section dimension), we also consider the application of the cross section dependence test (CD) proposed by Pesaran (2004). In Monte Carlo experiments it emerges that for most combinations of N and T the CD test is correctly sized, whereas the validity of the LM test requires T (time series dimension) to be quite large relative to N. We illustrate the crosssectional independence tests by an application to a probit panel of rollcall votes in the U. S. Congress and find that the votes display a significant degree of cross section dependence.
JEL Classifications: C12, C33, C35
Key Words: Nonlinear panels, cross section dependence, probit and Tobit models
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/wp10/CDP_28July2010.pdf

"Lumpy Price Adjustments: A Microeconometric Analysis", Emmanuel Dhyney, Catherine Fuss, M. Hashem Pesaran, Patrick Sevestre April, 2007, Revised August 2008
Abstract: This paper presents a simple model of statedependent pricing that allows identification of the relative importance of the degree of price rigidity that is inherent to the price setting mechanism (intrinsic) and that which is due to the price’s driving variables (extrinsic). Using two data sets consisting of a large fraction of the price quotes used to compute the Belgian and French CPI, we are able to assess the role of intrinsic and extrinsic price stickiness in explaining the occurrence and magnitude of price changes at the outlet level. We find that infrequent price changes are not necessarily associated with large adjustment costs. Indeed, extrinsic rigidity appears to be significant in many cases. We also find that asymmetry in the price adjustment could be due to trends in marginal costs and/or desired markups rather than asymmetric cost of adjustment bands.
JEL Classifications: C51, C81, D21
Key Words: Sticky prices, nominal intrinsic and extrinsic rigidities, micro non linear panels
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/wp08/LumpyPriceAdjustments14Aug08.pdf

"Large Panels with Common Factors and Spatial Correlation", M. Hashem Pesaran and Elisa Tosseti August, 2007, revised May 2010
Abstract: This paper considers methods for estimating the slope coeficients in large panel data models that are robust to the presence of various forms of error cross section dependence. It introduces a general framework where error cross section dependence may arise because of unobserved common effects and/or error spillover effects due to spatial or other forms of local dependencies. Initially, this paper focuses on a panel regression model where the idiosyncratic errors are spatially dependent and possibly serially correlated, and derives the asymptotic distributions of the mean group and pooled estimators under heterogeneous and homogeneous slope coeficients, and for these estimators proposes nonparametric variance matrix estimators. The paper then considers the more general case of a panel data model with a multifactor error structure and spatial error correlations. Under this framework, the Common Correlated Effects (CCE) estimator, recently advanced by Pesaran (2006), continues to yield estimates of the slope coeficients that are consistent and asymptotically normal. Small sample properties of the estimators under various patterns of cross section dependence, including spatial forms, are investigated by Monte Carlo experiments. Results show that the CCE approach works well in the presence of weak and/or strong cross sectionally correlated errors.
JEL Classifications: C10, C31, C33
Key Words: Panels, Common Factors, Spatial Dependence, Common Correlated Effects Estimator.
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/wp10/PesaranTosetti31may10.pdf

"Variable Selection, Estimation and Inference for Multiperiod Forecasting Problems", by M. Hashem Pesaran, A. Pick and A. Timmerman. April, 2010
Abstract: This paper conducts a broadbased comparison of iterated and direct multiperiod forecasting approaches applied to both univariate and multivariate models in the form of parsimonious factoraugmented vector autoregressions. To account for serial correlation in the residuals of the multiperiod direct forecasting models we propose a new SURE based estimation method and modified Akaike information criteria for model selection. Empirical analysis of the 170 variables studied by Marcellino, Stock and Watson (2006) shows that information in factors helps improve forecasting performance for most types of economic variables although it can also lead to larger biases. It also shows that finitesample modifications to the Akaike information criterion can modestly improve the performance of the direct multiperiod forecasts.
JEL Classifications: C22, C32, C52, C53
Key Words: Multiperiod forecasts, direct and iterated methods, factor augmented VARs
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/wp10/pptiterated_24april_2010.pdf

"Panels With Nonstationary Multifactor Error Structures" , by G. Kapetanios, M. Hashem Pesaran and T. Yamagata July, 2006, Revised June 2009
Abstract: The presence of crosssectionally correlated error terms invalidates much inferential theory of panel data models. Recently, work by Pesaran (2006) has suggested a method which makes use of crosssectional averages to provide valid inference in the case of stationary panel regressions with a multifactor error structure. This paper extends this work and examines the important case where the unobservable common factors follow unit root processes. The extension to the I(1) processes is remarkable on two counts. Firstly, it is of great interest to note that while intermediate results needed for deriving the asymptotic distribution of the panel estimators differ between the I(1) and I(0) cases, the final results are surprisingly similar. This is in direct contrast to the standard distributional results for I(1) processes that radically differ from those for I(0) processes. Secondly, it is worth noting the significant extra technical demands required to prove the new results. The theoretical findings are further supported for small samples via an extensive Monte Carlo study. In particular, the results of the Monte Carlo study suggest that the crosssectional average based method is robust to a wide variety of data generation processes and has
lower biases than the alternative estimation methods considered in the paper.
JEL Classifications: C12, C13, C33.
Key Words:Cross Section Dependence, Large Panels, Unit Roots, Principal Components, Common Correlated E¤ects.
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/wp09/KPY_CCEunit_130609.pdf

"Spatial and Temporal Diffusion of House Prices in the UK", by Sean Holly, M. Hashem Pesaran and Takashi Yamagata. December, 2009
Abstract: This paper provides a method for the analysis of the spatial and temporal diffusion of shocks in a dynamic system. We use changes in real house prices within the UK economy at the level of regions to illustrate its use. Adjustment to shocks involves both a region specific and a spatial effect. Shocks to a dominant region  London  are propagated contemporaneously and spatially to other regions. They in turn impact on other regions with a delay. We allow for lagged effects to echo back to the dominant region. London in turn is influenced by international developments through its link to New York and other financial centers. It is shown that New York house prices have a direct effect on London house prices. We analyse the effect of shocks using generalised spatiotemporal impulse responses. These highlight the diffusion of shocks both over time (as with the conventional impulse responses) and over space.
Key Words: House Prices, Cross Sectional Dependence, Spatial Dependence.
JEL Classifications: C21, C23
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/wp09/UKhouseprices_December 9 2009.pdf

"Predictability of Asset Returns and the Efficient Market Hypothesis", by M. Hashem Pesaran. May, 2010
Abstract: This paper is concerned with empirical and theoretical basis of the Efficient Market Hypothesis (EMH). The paper begins with an overview of the statistical properties of asset returns at di¤erent frequencies (daily, weekly and monthly), and considers the evidence on return predictability, risk aversion and market efficiency. The paper then focuses on the theoretical foundation of the EMH, and show that market efficiency could coexit with heterogeneous beliefs and individual irrationality so long as individual errors are cross sectionally weakly dependent in the sense defined by Chudik, Pesaran, and Tosetti (2010). But at times of market euphoria or gloom these individual errors are likely to become cross sectionally strongly dependent and the collective outcome could display significant departures from market e¢ ciency. Market efficiency could be the norm, but it is likely to be punctuated with episodes of bubbles and crashes. The paper also considers if market inefficiencies (assuming that they exist) can be exploited for profit.
JEL Classifications: G12, G14
Key Words: Market Efficiency, Predictability, Heterogeneity of Expectations, Forecast averaging, Equity Premium Puzzle.
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/wp10/AssetReturnsMEH31May2010.pdf

"Weak and Strong Cross Section Dependence and Estimation of Large Panels", by Alexander Chudik, M. Hashem Pesaran and Elisa Tosetti April, 2010
Abstract: This paper introduces the concepts of timespecific weak and strong cross section dependence, and investigates how these notions are related to the concepts of weak, strong and semistrong common factors, frequently used for modelling residual cross section correlations in panel data models. It then focuses on the problems of estimating slope coefficients in large panels, where cross section units are subject to possibly a large number of unobserved common factors. It is established that the Common Correlated Effects (CCE) estimator introduced by Pesaran (2006) remains asymptotically normal under certain conditions on factors loadings of an infinite factor error structure, including cases where methods relying on principal components fail. The paper concludes with a set of Monte Carlo experiments where the small sample properties of estimators based on principal components and CCE estimators are investigated and compared under various assumptions on the nature of the unobserved common effects.
JEL Classifications: Panels, Strong and Weak Cross Section Dependence, Weak and Strong Factors, Common Correlated E¤ects (CCE) Estimator.
Key Words: C10, C31, C33.
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/wp10/CPT_StrongWeakCSD_19April10.pdf

"Infinite Dimensional VARs and Factor Models", Alexander Chudik and M. Hashem Pesaran. November, 2007, Revised October 2008
Abstract: This paper introduces a novel approach for dealing with the ‘curse of dimensionality’ in the case of large linear dynamic systems. Restrictions on the coeficients of an unrestricted VAR are proposed that are binding only in a limit as the number of endogenous variables tends to infinity. It is shown that under such restrictions, an infinitedimensional VAR (or IVAR) can be arbitrarily well characterized by a large number of finitedimensional models in the spirit of the global VAR model proposed in Pesaran et al. (JBES, 2004). The paper also considers IVAR models with dominant individual units and shows that this will lead to a dynamic factor model with the dominant unit acting as the factor. The problems of estimation and inference in a stationary IVAR with unknown number of unobserved common factors are also investigated. A cross section augmented least squares estimator is proposed and its asymptotic distribution is derived. Satisfactory small sample properties are documented by Monte Carlo experiments.
JEL Classifications: C10, C33, C51
Key Words: Large N and T Panels, Weak and Strong Cross Section Dependence, VAR, Global, VAR, Factor Models.
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/wp10/ChudikPesaran_RevisedPaper_22Jan10.pdf

"Forecasting Random Walks Under Drift Instability", by M. Hashem Pesaran and Andreas Pick. March, 2008, Revised January 2009
Abstract: This paper considers forecast averaging when the same model is used but estimation is carried out over different estimation windows. It develops theoretical results for random walks when their drift and/or volatility are subject to one or more structural breaks. It is shown that compared to using forecasts based on a single estimation window, averaging over estimation windows leads to a lower bias and to a lower root mean square forecast error for all but the smallest of breaks. Similar results are also obtained when observations are exponentially downweighted, although in this case the performance of forecasts based on exponential downweighting critically depends on the choice of the weighting coeficient. The forecasting techniques are applied to 20 weekly series of stock market futures and it is found that average forecasting methods in general perform better than using forecasts based on a single estimation window.
Key Words: Forecast combinations, averaging over estimation windows, exponentially downweighting observations, structural breaks.
JEL Classifications: C22, C53.
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/wp09/AveWExpW20Jan09.pdf
Abstract: This paper applies the modelling strategy of Garratt, Lee, Pesaran and Shin (2003) to the estimation of a structural cointegrated VAR model that relates the core macroeconomic variables of the Swiss economy to current and lagged values of a number of key foreign variables. We identify and test a longrun structure between the variables. Moreover, we analyse the dynamic properties of the model using Generalised Impulse Response Functions. In its current form the model can be used to produce forecasts for the endogenous variables either under alternative specifications of the marginal model for the exogenous variables, or conditional on some prespecified path of those variables (for scenario forecasting). In due course the Swiss VECX* model can also be integrated within a Global VAR (GVAR) model where the foreign variables of the model are determined endogenously.
Key Words: Longrun structural vector autoregression.
JEL Classifications: C53, C32.
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/wp08/SwissVECXModel(21Feb08).pdf

"A VECX* Model of the Swiss Economy", by Katrin AssenmacherWesche and M. Hashem Pesaran. February, 2008

"Modelling Volatilities and Conditional Correlations in Futures Markets with a Multivariate t Distribution", Bahram Pesaran and M. Hashem Pesaran June, 2007
Abstract: This paper considers a multivariate t version of the Gaussian dynamic conditional correlation (DCC) model proposed by Engle (2002), and suggests the use of devolatized returns computed as returns standardized by realized volatilities rather than by GARCH type volatility estimates. The tDCC estimation procedure is applied to a portfolio of daily returns on currency futures, government bonds and equity index futures. The results strongly reject the normalDCC model in favour of a tDCC specification. The tDCC model also passes a number of VaR diagnostic tests over an evaluation sample. The estimation results suggest a general trend towards a lower level of return volatility, accompanied by a rising trend in conditional cross correlations in most markets; possibly reflecting the advent of euro in 1999 and increased interdependence of financial markets.
JEL Classifications: C51, C52, G11
Key Words: Volatilities and Correlations, Futures Market, Multivariate t, Financial Interdependence, VaR diagnostics.
Full Text: http://www.econ.cam.ac.uk/emeritus/mhp1/wp2007/PP_TDCC(28Jun07).pdf