Yogurts Choose Consumers? Estimation of Random Utility Models via Two-Sided Matching
Posted: 9 Mar 2017
Date Written: May 16, 2018
We show that the problem of demand inversion – a crucial step in the estima tion of random utility-based discrete-choice demand and dynamic discrete-choice models – is equivalent to the determination of stable outcomes in matching models. This general result applies to random utility models that are not necessarily additive, smooth, nor even invertible. Based on this equivalence, algorithms for the determination of stable matchings can provide eﬀective computational methods for estimating these models. For discrete choice models which are not invertible, we show that the identiﬁed set of utility vectors is a lattice, and the matching algorithms recover sharp upper and lower bounds on the utilities. For models which are invertible, the matching approach permits estimation of models that were previously diﬃcult to estimate, such as the pure characteristics model.
Keywords: random utility models, demand inversion, two-sided matching, discrete choice demand models, partial identiﬁcation, pure characteristics model
JEL Classification: C51, C60
Suggested Citation: Suggested Citation