Robust Semiparametric Estimation in Panel Multinomial Choice Models
76 Pages Posted: 12 Dec 2018 Last revised: 7 Mar 2019
Date Written: January 31, 2019
This paper proposes a simple and robust method for semiparametric identification and estimation in a panel multinomial choice model, where we allow for infinite-dimensional fixed effects that enter into consumer utilities in an additively nonseparabe way, thus incorporating rich forms of unobserved heterogeneity. Our identification strategy exploits multivariate monotonicity in an index vector of observable characteristics, and uses the logical contraposition of an intertemporal inequality on choice probabilities to obtain identifying restrictions on the indexes. We provide consistent estimators based on our identification strategy, together with a computational procedure that exploits a combination of theoretical and practical advantages under a spherical-coordinate reparameterization. A simulation study and an empirical illustration with the Nielsen data are conducted to analyze the finite-sample performance of our estimation method and demonstrate the adequacy of our computational procedure for practical implementation.
Keywords: semiparametric estimation, panel multinomial choice, infinite-dimensional unobserved heterogeneity, nonseparability, monotonicity, spherical coordinates
JEL Classification: C01, C14, C23, C63, L81, M31
Suggested Citation: Suggested Citation