Footnote:
Nach Informationen von SSRN wurde die ursprüngliche Fassung des Dokuments September 16, 2015 erstellt
Description:
The problem of demand inversion -- a crucial step in the estimation of randomutility discrete-choice models -- is equivalent to the determination of stable outcomes intwo-sided matching models. This equivalence applies to random utility models that are notnecessarily additive, smooth, nor even invertible. Based on this equivalence, algorithmsfor the determination of stable matchings provide e ffective computational methods forestimating these models. For non-invertible models, the identifi ed set of utility vectorsis a lattice, and the matching algorithms recover sharp upper and lower bounds on theutilities. For invertible models, our matching approach facilitates estimation of models thatwere previously di cult to estimate, such as the pure characteristics model. An empiricalapplication to voting data from the 1999 European Parliament elections illustrates thegood performance of our matching-based demand inversion algorithms in practice