Estimating Price Elasticities with Theory-Based Priors
We show how price elasticity estimates can be improved in demand systems involving multiple brands and stores. We treat these demand models in a hierarchical Bayesian framework. Unlike more standard Bayesian hierarchical treatments, we utilize prior information based on the restrictions imposed by additive utility models. In an additive utility model approach, price elasticities are driven by a general substitution parameter as well as brand specific expenditure elasticities. We employ a differential shrinkage approach in which price elasticities are held closely to the restrictions of the additive utility theory while store-to-store variation is accomodated via differences in expenditure elasticities. Application of our new methods to simulated and real store scanner data show significant improvements over existing Bayesian and non-Bayesian methods.
This is the pre-peer-reviewed version of the following article:
Alan L. Montgomery and Peter E. Rossi (Nov 1999), "Estimating Price Elasticities with Theory-Based Priors", Journal of Marketing Research 36, 4; ABI/INFORM Complete pg. 413, which has been published in final form at Journal of Marketing Research.