Title: Inference in Microeconometric Models (MiMo)

Sponsor: European Research Council (ERC), Starting Grant

Description: Unobserved differences between economic agents are an important driver behind the differences in their economic outcomes such as schooling decisions, wages, and employment durations. Allowing for such unobserved heterogeneity in economic modelling equips the specification with an additional dimension of realism but presents major challenges for econometric practice. Hence, reconciling heterogeneity in the data with econometric models is an issue of utmost importance.

The aim of this project is to develop inference methods for models with unobserved heterogeneity by exploiting the identifying power of longitudinal (panel) data. The project consists of three Work Packages (WP). Together, they span the largest part of modern applications of panel data.

The first WP deals with inference on nonlinear models and enhances the performance of statistical hypothesis tests. So far, the literature has focused on point estimation. However, it is statistical inference that accounts for uncertainty in the data and forms the basis for testing economic restrictions. The second WP makes progress on the estimation of models for network data. The importance of social and economic connections is well established but few formal results are available. We exploit the fact that network data can be seen as a type of panel data to derive such results. The third WP uses panel data to identify and nonparametrically estimate dynamic discrete-choice models with unobserved type heterogeneity and/or latent state variables. Such results are inexistent even though dynamic discrete-choice models are a workhorse tool in labor economics and industrial organization.

The performance of the tools will be assessed theoretically and via simulation, and they will be applied to various empirical problems. Two examples of applications that we will study are the extensive margin of labor force participation and the determinants of the import and export behavior of firms and countries. We begin with a state-of-the-art and list main challenges in the existing literature. In Section b we proceed with a discussion on how the current project will address these challenges. For clarity, we deal with each of the three topics outlined above separately.

---

Published Papers

Jochmans, K. A Portmanteau Test for Serial Correlation in Short Panels, (2020) Econometric Theory, forthcoming
Jochmans, K. Testing for Correlation in Error‐Component Models, (2020) Journal of Applied Econometrics
Jochmans, K. Heteroskedasticity-Robust Inference in Linear Regression Models with many Covariates, (2020) Journal of the American Statistical Association
Jochmans, K. and Verardi, V. xtserialpm: A Portmanteau Test for Serial Correlation in a Linear Panel Model, (2020) Stata Journal
Jochmans, K. and Verardi, V. twexp and twgravity: Fitting Exponential Regression Models with Two-way Fixed Effects, (2020) Stata Journal
Jochmans, K. and Otsu, T. Likelihood Corrections for Two-way Models, (2019) Annals of Economics and Statistics
Jochmans, K. and Weidner, M. Fixed-Effect Regressions on Network Data, (2019) Econometrica
Bonhomme, S. and Jochmans, K. and Robin, J-M. Nonparametric Estimation of Non-Exchangeable Latent-Variable Models, (2017) Journal of Econometrics
Jochmans, K. and Magnac, T. A Note on Sufficiency in Binary Panel Models, (2017) Econometrics Journal
Jochmans, K. Semiparametric Analysis of Network Formation, (2018) Journal of Business and Economic Statistics
Bonhomme, S. and Jochmans, K. and Robin, J-M. Non-parametric Estimation of Finite Mixtures from Repeated Measurements, (2016) Journal of the Royal Statistical Society - Series B

Cambridge Working Papers in Economics

Jochmans, K., Verardi, V. Instrumental-Variable Estimation of Gravity Equations, (2019) CWPE1994
Jochmans, K. Testing for Correlation in Error-Component Models, (2019) CWPE1993
Jochmans, K. Heteroskedasticity-Robust Inference in Linear Regression Models, (2019) CWPE1957
Jochmans, K. and Verardi, V. twexp and twgravity: Estimating exponential regression models with two-way fixed effects, (2019) CWPE1945
Jochmans, K. and Verardi, V. xtserialpm: A portmanteau test for serial correlation in a linear panel model, (2019) CWPE1944
Jochmans, K. and Weidner, M. Fixed-Effect Regressions on Network Data, (2019) CWPE1938
Jochmans, K. Testing for Correlation in Error-Component Models, (2019) CWPE1910
Jochmans, K., Otsu, T. Likelihood Corrections for Two-way Models, (2018) CWPE1887
Jochmans, K. A Portmanteau Test for Correlation in Short Panels, (2018) CWPE1886

Software Components

Jochmans, K. and Verardi, V. "RASSIGN: Stata module to perform regression-based test for random assignment to peer groups" (2020) Statistical Software Components S458754, Boston College Department of Economics.
Jochmans, K. and Verardi, V. "IVGRAVITY: Stata module containing method-of-moment IV estimators of exponential-regression models with two-way fixed effects from a cross-section of data on dyadic interactions and endogenous covaria" (2019) S458698, Boston College Department of Economics.
Verardi, V. and Jochmans, K. "TWGRAVITY: Stata module to estimate exponential-regression models with two-way fixed effects from a cross-section of data on dyadic interactions" (2019) S458640, Boston College Department of Economics, revised 14 Oct 2019.
Jochmans, K. and Verardi, V. "XTSERIALPM: Stata module to perform a portmanteau test for serial correlation in panel data" (2019) S458642, Boston College Department of Economics.
Verardi, V. and Jochmans, K. "TWEXP: Stata module to estimate exponential-regression models with two-way fixed effects," (2019) S458641, Boston College Department of Economics, revised 23 Aug.