Research Projects
-
Project: Demand for Cars and Their Attributes
Funded by: Department for Transport.Project Description (DfT approved):
This project, undertaken by a team led by Cambridge Econometrics, identified how the decision to purchase a new car responds to changes in: the purchase price of cars; the fixed costs of motoring (eg insurance, vehicle excise duty); and the variable costs of motoring (eg maintenance, fuel costs). To establish a robust dataset with variation in both household and car attributes, BMRB undertook a bespoke survey of households that had recently purchased a new vehicle.
Using the survey data, Dr Melvyn Weeks (University of Cambridge) applied econometric methods to estimate the parameters of discrete choice models of vehicle demand. Mixed logit modelling techniques were used to estimate own and cross-price elasticities, based upon the approach developed by Prof Kenneth Train (University of California) which has become the best-practice method in the US for forecasting of vehicle demand, energy use, CO2 emissions, and penetration of alternative fuelled vehicles. Prof Train was part of our project team, providing advice on the design, implementation and interpretation of the results.
The project delivered to the Department for Transport estimates of own and cross-price elasticities to be used in analyses of the responsiveness to vehicle demand to changes in vehicle attributes.
Software: All model parameters and own/cross-elasticities were estimated using the DCM discrete choice software written by Dr. Melvyn Weeks and Dr. Matias Eklof.Final Report:
http://www.dft.gov.uk/pgr/economics/rdg/Press: Daily Telegraph.
http://www.telegraph.co.uk/earth/main.jhtml;jsessionid=FMEYYPGWRXTZDQFIQMGCFF4AVCBQUIV0?xml=/earth/2008/01/26/eacar126.xmlThe Times.
http://driving.timesonline.co.uk/tol/life_and_style/driving/news/article3267180.eceLow Carbon Vehicle Partnership.
http://www.lowcvp.org.uk/news/835/new-research-shows-consumers-willing-to-pay-more-for-%20higher-fuel-economy/ - ESRC Funded Project: An Experimental Approach to Imputing Missing Data has just been completed. There are two initial research outputs. These are
Methods of Imputation For Missing Data and
Missing Observations in Survey Data: An Experimental Approach to Imputation - joint with Alan Hughes
The End of Award Report Report is also available
- Model Uncertainty Project