Improving the performance of random coefficients demand models : the role of optimal instrumentsImproving the performance of random coefficients demand models : the role of optimal instruments
Faculty of Applied Economics
Faculteit Toegepaste Economische Wetenschappen
Antwerp :UA, 2012[*]2012
Research paper / UA, Faculty of Applied Economics ; 2012:011
University of Antwerp
We shed new light on the performance of Berry, Levinsohn and Pakes’ (1995) GMM esti- mator of the aggregate random coe¢ cient logit model. Based on an extensive Monte Carlo study, we show that the use of Chamberlain’s (1987) optimal instruments overcomes most of the problems that have recently been documented with standard, non-optimal instruments. Op- timal instruments reduce small sample bias, but prove even more powerful in increasing the estimator’s e¢ ciency and stability. Other recent methodological advances (MPEC, polynomial- based integration of the market shares) greatly improve computational speed, but they are only successful in terms of bias and e¢ ciency when combined with optimal instruments.