Semiparametric estimation of a class of generalized linear models without smoothing

In a generalized linear model, the mean of the response variable is a possibly non-linear function of a linear combination of explanatory variables. When the nonlinear function is unknown and is estimated nonparametrically from the data, these models are known as single index models. Using the relation of generalized linear models with the exponential family model, this paper shows how to use a modified version of the empirical cumulant generating function to estimate the linear function of the explanatory variables with no need of smoothing techniques. The resulting estimator is consistent and normally distributed. Extensive simulations, partially reported here, show that the method works in practice. The method can also be seen as complementary to existing fully nonparametric methods. In fact, it can provide an initial value that can be used to fine tune a nonparametric estimator of the link function in the first step of the estimation.

[1]  B. Jørgensen,et al.  Some properties of exponential dispersion models , 1986 .

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

[3]  Lixing Zhu,et al.  Composite Quantile Regression for the Single-Index Model , 2013 .

[4]  L. Hansen.  Large Sample Properties of Generalized Method of Moments Estimators , 1982 .

[5]  A. V. D. Vaart.  Asymptotic Statistics: Delta Method , 1998 .

[6]  Riccardo Poli,et al.  Foundations of Genetic Programming , 1999, Springer Berlin Heidelberg.

[7]  C. C. Heyde,et al.  Quasi-Likelihood and Optimal Estimation, Correspondent Paper , 1987 .

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

[9]  Shakeeb Khan,et al.  Distribution Free Estimation of Heteroskedastic Binary Response Models Using Probit/Logit Criterion Functions , 2013 .

[10]  W. Härdle,et al.  Direct Semiparametric Estimation of Single-Index Models with Discrete Covariates dpsfb950075.ps.tar = Enno MAMMEN J.S. MARRON: Mass Recentered Kernel Smoothers , 1996 .

[11]  P. Gänssler.  Weak Convergence and Empirical Processes - A. W. van der Vaart; J. A. Wellner. , 1997 .

[12]  Yingcun Xia,et al.  ASYMPTOTIC DISTRIBUTIONS FOR TWO ESTIMATORS OF THE SINGLE-INDEX MODEL , 2006, Econometric Theory.

[13]  Richard H. Byrd,et al.  A Trust Region Algorithm for Nonlinearly Constrained Optimization , 1987 .

[14]  W. Newey,et al.  Uniform Convergence in Probability and Stochastic Equicontinuity , 1991 .

[15]  Gary Chamberlain,et al.  Binary Response Models for Panel Data: Identification and Information , 2010 .

[16]  James G. MacKinnon,et al.  Convenient Specification Tests for Logit and Probit Models , 1984 .

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

[18]  Br Uce E. Ha,et al.  UNIFORM CONVERGENCE RATES FOR KERNEL ESTIMATION WITH DEPENDENT DATA , 2008 .

[19]  A. Juditsky,et al.  Direct estimation of the index coefficient in a single-index model , 2001 .

[20]  P. McCullagh,et al.  Generalized Linear Models , 1984 .

[21]  Lixing Zhu,et al.  The EFM approach for single-index models , 2011, 1211.5220.

[22]  M. Gerfin.  Parametric and semi‐parametric estimation of the binary response model of labour market participation , 1996 .

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

[24]  Thomas M. Stoker,et al.  Investigating Smooth Multiple Regression by the Method of Average Derivatives , 2015 .

[25]  W. Härdle,et al.  Optimal Smoothing in Single-index Models , 1993 .

[26]  D. Pollard,et al.  Cube Root Asymptotics , 1990 .

[27]  C. C. Heyde,et al.  Quasi-likelihood and Optimal Estimation , 2010 .

[28]  Jianqing Fan,et al.  Generalized Partially Linear Single-Index Models , 1997 .

[29]  J. Friedman.  Greedy function approximation: A gradient boosting machine. , 2001 .

[30]  B. Jørgensen.  Exponential Dispersion Models , 1987 .