Identifying Heterogeneity in Economic Choice and Selection Models Using Mixtures

independence of a class of economic choice models. We state an economic property known as reducibility and prove that reducibility ensures linear independence and hence identification. Reducibility makes verifying the identification of nonlinear models easy. We use our mixtures framework to prove identification in three classes of economic models: 1) continuous outcomes including simultaneous equations, 2) multinomial discrete choice, and 3) selection and mixed continuous-discrete choice. We rely on linear independence, not identification at infinity. For selection, we allow for essential heterogeneity in both the selection and outcome equations and fully identify the joint distribution of outcomes.

[1]  J. Heckman,et al.  Instrumental Variables, Selection Models, and Tight Bounds on the Average Treatment Effect , 2000 .

[2]  Donald W. K. Andrews,et al.  Semiparametric Estimation of the Intercept of a Sample Selection Model , 1998 .

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

[4]  Lung-fei Lee,et al.  Semiparametric maximum likelihood estimation of polychotomous and sequential choice models , 1995 .

[5]  V. Susarla,et al.  Estimation of a mixing distribution function , 1977 .

[6]  Enno Mammen,et al.  ANALYZING THE RANDOM COEFFICIENT MODEL NONPARAMETRICALLY , 2009, Econometric Theory.

[7]  G. Chamberlain.  Asymptotic efficiency in semi-parametric models with censoring , 1986 .

[8]  W. Thomsen,et al.  A Characterization of Identifiability of Mixtures of Distributions , 1987 .

[9]  M. Gentzkow.  Valuing New Goods in a Model with Complementarity: Online Newspapers , 2007 .

[10]  J J Heckman,et al.  Local instrumental variables and latent variable models for identifying and bounding treatment effects. , 1999, Proceedings of the National Academy of Sciences of the United States of America.

[11]  Nonparametric Identification and Estimation in a Generalized Roy Model , 2008 .

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

[13]  H. Teicher.  Identifiability of Mixtures of Product Measures , 1967 .

[14]  H. Wold,et al.  Some Theorems on Distribution Functions , 1936 .

[15]  Edward Vytlacil,et al.  Dummy Endogenous Variables in Weakly Separable Models , 2007 .

[16]  E. Tamer,et al.  Endogenous binary choice model with median restrictions , 2003 .

[17]  Geert Ridder,et al.  The Non-Parametric Identification of Generalized Accelerated Failure-Time Models , 1990 .

[18]  J. Heckman,et al.  Making the Most out of Programme Evaluations and Social Experiments: Accounting for Heterogeneity in Programme Impacts , 1997 .

[19]  C. Manski.  MAXIMUM SCORE ESTIMATION OF THE STOCHASTIC UTILITY MODEL OF CHOICE , 1975 .

[20]  R. Beran,et al.  Minimum Distance Estimation in Random Coefficient Regression Models , 1994 .

[21]  Pradeep K. Chintagunta,et al.  Nonparametric Discrete Choice Models With Unobserved Heterogeneity , 2010 .

[22]  H. Ichimura,et al.  Maximum likelihood estimation of a binary choice model with random coefficients of unknown distribution , 1998 .

[23]  D. Wise,et al.  A CONDITIONAL PROBIT MODEL FOR QUALITATIVE CHOICE: DISCRETE DECISIONS RECOGNIZING INTERDEPENDENCE AND HETEROGENEOUS PREFERENCES' , 1978 .

[24]  Harold R. Parks,et al.  A Primer of Real Analytic Functions , 1992 .

[25]  Jeffrey A. Dubin,et al.  An Econometric Analysis of Residential Electric Appliance Holdings and Consumption , 1984 .

[26]  James J Heckman,et al.  Understanding Instrumental Variables in Models with Essential Heterogeneity , 2006, The Review of Economics and Statistics.

[27]  Jean-Pierre Dubé.  Multiple Discreteness and Product Differentiation: Demand for Carbonated Soft Drinks , 2004 .

[28]  H. James.  VARIETIES OF SELECTION BIAS , 1990 .

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

[30]  J. Angrist,et al.  Identification and Estimation of Local Average Treatment Effects , 1995 .

[31]  Costas Meghir,et al.  Identification of Treatment Effects Using Control Functions in Models with Continuous, Endogenous Treatment and Heterogeneous Effects , 2008 .

[32]  J. Wooldridge.  Instrumental variables estimation of the average treatment effect in the correlated random coefficient model , 2008 .

[33]  Bo E. Honoré,et al.  The Empirical Content of the Roy Model , 1990 .

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

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

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

[37]  Jstor,et al.  Invention in the Industrial Research Laboratory , 1963, Journal of Political Economy.

[38]  S. Cosslett.  DISTRIBUTION-FREE MAXIMUM LIKELIHOOD ESTIMATOR OF THE BINARY CHOICE MODEL1 , 1983 .

[39]  D. McFadden.  Conditional logit analysis of qualitative choice behavior , 1972 .

[40]  Jeremy T. Fox,et al.  Linear Regression Estimation of Discrete Choice Models with Nonparametric Distributions of Random Coefficients , 2007 .

[41]  Steven Berry,et al.  The Pure Characteristics Demand Model , 2007 .

[42]  Rosa L. Matzkin.  Nonparametric identification and estimation of polychotomous choice models , 1993 .

[43]  James J. Heckman,et al.  Understanding Instrumental Variables in Models with Essential Heterogeneity , 2006 .

[44]  J. Heckman.  Sample selection bias as a specification error , 1979 .

[45]  Nonparametric estimation of mixing densities for discrete distributions , 2005, math/0602217.

[46]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[47]  Gerard J. van den Berg,et al.  The identifiability of the mixed proportional hazards competing risks model , 2003 .

[48]  E. Vytlacil,et al.  Threshold Crossing Models and Bounds on Treatment Effects: A Nonparametric Analysis , 2005 .

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

[50]  S. Yakowitz,et al.  On the Identifiability of Finite Mixtures , 1968 .

[51]  Heleno Martins Pioner.  Semiparametric Identification of Multidimensional Screening Models , 2008 .

[52]  R. Gronau.  Wage Comparisons--A Selectivity Bias , 1973, Journal of Political Economy.

[53]  Andrew R. Barron,et al.  Mixture Density Estimation , 1999, NIPS.

[54]  Demian Pouzo,et al.  Efficient Estimation of Semiparametric Conditional Moment Models with Possibly Nonsmooth Residuals , 2008 .

[55]  J J Heckman,et al.  Econometric mixture models and more general models for unobservables in duration analysis , 1994, Statistical methods in medical research.

[56]  K. Roeder,et al.  Uniqueness of estimation and identifiability in mixture models , 1993 .

[57]  N. Laird.  Nonparametric Maximum Likelihood Estimation of a Mixing Distribution , 1978 .

[58]  I. Hendel,et al.  Estimating Multiple-Discrete Choice Models: An Application to Computeri-Zzation Returns , 1994 .

[59]  J. Heckman.  Shadow prices, market wages, and labor supply , 1974 .

[60]  P. Barbe.  Statistical Analysis of Mixtures and the Empirical Probability Measure , 1998 .

[61]  James J. Heckman,et al.  Testing the Mixture of Exponentials Hypothesis and Estimating the Mixing Distribution by the Method of Moments , 1990 .

[62]  T. Thompson.  IDENTIFICATION OF SEMIPARAMETRIC DISCRETE CHOICE MODELS , 1989 .

[63]  N. E. Day.  Estimating the components of a mixture of normal distributions , 1969 .

[64]  Ting Zhu,et al.  Complementarities and the Demand for Home Broadband Internet Services , 2008, Mark. Sci..

[65]  C. Manski,et al.  Monotone Instrumental Variables with an Application to the Returns to Schooling , 1998 .

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

[67]  Kim C. Border,et al.  Infinite Dimensional Analysis: A Hitchhiker’s Guide , 1994 .

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

[69]  Shakeeb Khan,et al.  Irregular Identification, Support Conditions, and Inverse Weight Estimation , 2010 .

[70]  V. Chernozhukov,et al.  An IV Model of Quantile Treatment Effects , 2002 .

[71]  G. M. Tallis,et al.  Identifiability of mixtures , 1982, Journal of the Australian Mathematical Society. Series A. Pure Mathematics and Statistics.

[72]  Steven Berry,et al.  On the Nonparametic Identification of Nonlinear Simultaneous Equations Models: Comment on B. Brown (1983) and Roehrig (1988) , 2004 .

[73]  W. Hanemann.  Discrete-Continuous Models of Consumer Demand , 1984 .

[74]  A. Lewbel,et al.  Semiparametric qualitative response model estimation with unknown heteroscedasticity or instrumental variables , 2000 .

[75]  R. Narasimhan,et al.  Several Complex Variables , 1971 .

[76]  Rosa L. Matzkin.  HETEROGENEOUS CHOICE , 2006 .

[77]  Steven Berry,et al.  Nonparametric Identi cation of Multinomial Choice Demand Models with Heterogeneous Consumers , 2008 .

[78]  Jeremy T. Fox,et al.  A Simple Nonparametric Estimator for the Distribution of Random Coefficients , 2007 .