Identification and information in monotone binary models

This paper considers binary response models where errors are uncorrelated with a set of instrumental variables and are independent of a continuous regressor v, conditional on all other variables. It is shown that these exclusion restrictions are not sufficient for identification and that additional identifying assumptions are needed. Such an assumption, introduced by Lewbel [Semiparametric qualitative response model estimation with unknown heteroskedasticity or instrumental variables. Journal of Econometrics 97, 145-177], is that the support of the continuous regressor is large, but we show that it significantly restricts the class of binary phenomena which can be analysed. We propose an alternative additional assumption under which β remains just identified and the estimation unchanged. This alternative assumption does not impose specific restrictions on the data, which broadens the scope of the estimation method in empirical work. The semiparametric efficiency bound of the model is also established and an existing estimator is shown to achieve that bound. The efficient estimator uses a plug-in density estimate. It is shown that plugging in the true density rather than an estimate is inefficient. Extensions to ordered choice models are provided.

[1]  Juan M. Rodriguez-Poo,et al.  Semiparametric Estimation of a Duration Model , 2001 .

[2]  S. Cosslett.  Efficiency Bounds for Distribution-free Estimators of the Binary , 1987 .

[3]  Bo E. Honoré,et al.  Semiparametric Binary Choice Panel Data Models without Strictly Exogeneous Regressors , 2000 .

[4]  J. Powell,et al.  c ○ 2004 The Review of Economic Studies Limited Endogeneity in Semiparametric Binary Response Models , 2001 .

[5]  P. Ruud.  Sufficient Conditions for the Consistency of Maximum Likelihood Estimation Despite Misspecifications of Distribution in Multinomial Discrete Choice Models , 1983 .

[6]  Gary Chamberlain,et al.  Efficiency Bounds for Semiparametric Regression , 1992 .

[7]  C. Manski.  Identification of Binary Response Models , 1988 .

[8]  J. Horowitz.  A Smoothed Maximum Score Estimator for the Binary Response Model , 1992 .

[9]  Francis Kramarz,et al.  Parameters of interest, nuisance parameters and orthogonality conditions An application to autoregressive error component models , 1997 .

[10]  C. Manski.  Semiparametric analysis of discrete response: Asymptotic properties of the maximum score estimator , 1985 .

[11]  Aaron K. Han.  Non-parametric analysis of a generalized regression model: the maximum rank correlation estimator , 1987 .

[12]  A. Lewbel,et al.  Endogenous selection or treatment model estimation , 2007 .

[13]  James L. Powell,et al.  Symmetrically Trimmed Least Squares Estimation For Tobit Models , 1986 .

[14]  W. Newey,et al.  The asymptotic variance of semiparametric estimators , 1994 .

[15]  H. Ichimura,et al.  SEMIPARAMETRIC LEAST SQUARES (SLS) AND WEIGHTED SLS ESTIMATION OF SINGLE-INDEX MODELS , 1993 .

[16]  Identi cation & Information in Monotone Binary Models , 2004 .

[17]  Susanne M. Schennach,et al.  A simple ordered data estimator for inverse density weighted expectations , 2007 .

[18]  G. Chamberlain.  Asymptotic efficiency in estimation with conditional moment restrictions , 1987 .

[19]  James L. Powell,et al.  Estimation of semiparametric models , 1994 .

[20]  R. Sherman,et al.  Rank estimators for monotonic index models , 1998 .

[21]  G. Imbens,et al.  Efficient Estimation of Average Treatment Effects Using the Estimated Propensity Score , 2000 .

[22]  E. Maurin.  The impact of parental income on early schooling transitions: A re-examination using data over three generations , 2002 .

[23]  Arthur Lewbel,et al.  Estimating Features of a Distribution from Binomial Data , 2001 .

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

[25]  T. Severini,et al.  A simplified approach to computing efficiency bounds in semiparametric models , 2001 .

[26]  Thomas M. Stoker,et al.  Semiparametric Latent Variable Model Estimation with Endogenous or Mismeasured Regressors , 2007 .

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

[28]  Thomas M. Stoker,et al.  Semiparametric Estimation of Index Coefficients , 1989 .

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

[30]  Mark B. Stewart,et al.  A comparison of semiparametric estimators for the ordered response model , 2005, Comput. Stat. Data Anal..

[31]  E. Maurin,et al.  Parental Income and School Attendance in a Low-Income Country: A semi-parametric analysis , 2001 .

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

[33]  R. Spady,et al.  AN EFFICIENT SEMIPARAMETRIC ESTIMATOR FOR BINARY RESPONSE MODELS , 1993 .

[34]  E. Vytlacil.  Independence, Monotonicity, and Latent Index Models: An Equivalence Result , 2002 .

[35]  T. Magnac,et al.  Partial Identification in Monotone Binary Models: Discrete Regressors and Interval Data , 2008 .

[36]  Qi Li,et al.  SEMIPARAMETRIC METHODS IN ECONOMETRICS , 2000, Econometric Theory.

[37]  Shakeeb Khan,et al.  WEIGHTED AND TWO-STAGE LEAST SQUARES ESTIMATION OF SEMIPARAMETRIC TRUNCATED REGRESSION MODELS , 2007, Econometric Theory.