ESTIMATION OF RANDOM-COEFFICIENT DEMAND MODELS: TWO EMPIRICISTS' PERSPECTIVE

• 成果类型: Article
• 署名作者: Knittel, Christopher R.; Metaxoglou, Konstantinos
• 署名单位: Massachusetts Institute of Technology (MIT); National Bureau of Economic Research
• 刊物名称: REVIEW OF ECONOMICS AND STATISTICS
• ISSN/ISSBN: 0034-6535
• DOI: 10.1162/REST_a_00394
• 发表日期: 2014-03
• 页码: 34-59
• 关键词: discrete-choice models; differentiated products; logit-models; welfare; MARKET; optimization; manufacturers; CONVERGENCE; COMPETITION; algorithms

摘要

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.