Estimation of Random-Coefficient Demand Models: Two Empiricists' Perspective
Author(s)Metaxoglou, Konstantinos; Knittel, Christopher Roland
MetadataShow full item record
We document the numerical challenges we experienced estimating random-coefficient demand models as in Berry, Levinsohn, and Pakes (1995) using two well-known data sets and a thorough optimization design. The optimization algorithms often converge at points where the first- and second-order optimality conditions fail. There are also cases of convergence at local optima. On convergence, the variation in the values of the parameter estimates translates into variation in the models' economic predictions. Price elasticities and changes in consumer and producer welfare following hypothetical merger exercises vary at least by a factor of 2 and up to a factor of 5.
DepartmentSloan School of Management
Review of Economics and Statistics
Knittel, Christopher R., and Konstantinos Metaxoglou. “Estimation of Random-Coefficient Demand Models: Two Empiricists’ Perspective.” Review of Economics and Statistics 96, no. 1 (March 2014): 34–59. © 2014 The President and Fellows of Harvard College and the Massachusetts Institute of Technology
Final published version