Linear Regression Estimation of Discrete Choice Models with Nonparametric Distributions of Random Coefficients

Random coefficient discrete choice models are a popular method for estimating demand in differentiated product markets. We introduce a computationally simple estimator that uses linear regression to estimate the distribution of random coefficients. The estimator is nonparametric for the distribution of the random coefficients. We compare our estimator to several alternatives in a Monte Carlo exercise, and find the estimator predicts out-of-sample market shares well. We discuss extensions to panel data and dynamic programming. ∗Bajari: Department of Economics, University of Minnesota, Twin Cities and NBER, 1035 Heller Hall, 271 19th Ave South, Minneapolis, MN 55455, email: bajari@econ.umn.edu; Fox: Department of Economics, University of Chicago, 1126 E. 59th St., Chicago, IL 60637, email: fox@uchicago.edu; Ryan: Massachusetts Institute of Technology and NBER, 50 Memorial Drive, E52-262C, Cambridge, MA 02142, email: sryan@mit.edu.

[1]  J. Heckman,et al.  A Method for Minimizing the Impact of Distributional Assumptions in Econometric Models for Duration Data , 1984 .

[2]  Diane Lambert,et al.  Generalizing Logistic Regression by Nonparametric Mixing , 1989 .

[3]  N. S. Cardell,et al.  Measuring the societal impacts of automobile downsizing , 1980 .

[4]  D. McFadden,et al.  MIXED MNL MODELS FOR DISCRETE RESPONSE , 2000 .

[5]  Peter E. Rossi,et al.  Bayesian Statistics and Marketing , 2005 .

[6]  Pradeep K. Chintagunta,et al.  Investigating Heterogeneity in Brand Preferences in Logit Models for Panel Data , 1991 .

[7]  Steven T. Berry,et al.  Automobile Prices in Market Equilibrium , 1995 .

[8]  Amil Petrin.  Quantifying the Benefits of New Products: The Case of the Minivan , 2001, Journal of Political Economy.

[9]  Eric Gautier,et al.  Nonparametric Estimation in Random Coefficients Binary Choice Models , 2009, 0907.2451.

[10]  Peter E. Rossi,et al.  Bayesian Statistics and Marketing: Rossi/Bayesian Statistics and Marketing , 2006 .

[11]  D. Andrews.  Asymptotic Normality of Series Estimators for Nonparametric and Semiparametric Regression Models , 1991 .

[12]  J. Boyd,et al.  THE EFFECT OF FUEL ECONOMY STANDARDS ON THE U.S. AUTOMOTIVE MARKET: AN HEDONIC DEMAND ANALYSIS , 1980 .

[13]  Daniel A. Ackerberg.  A new use of importance sampling to reduce computational burden in simulation estimation , 2001 .

[14]  John Rust.  Optimal Replacement of GMC Bus Engines: An Empirical Model of Harold Zurcher , 1987 .

[15]  Aviv Nevo.  Measuring Market Power in the Ready-to-Eat Cereal Industry , 1998 .

[16]  Kenneth Train,et al.  EM algorithms for nonparametric estimation of mixing distributions , 2008 .