论文信息 - Computer-assisted generalized partial linear models

Computer-assisted generalized partial linear models

A particular semiparametric model of interest is the generalized partial linear model (GPLM) which allows a nonparametric modeling of the influence of the continuous covariables. The paper reviews different estimation procedures based on kernel methods and test procedures on the correct specification of this model (vs. a parametric generalized linear model). Simulations and an application to a data set on East-West German migration illustrate similarities and dissimilarities of the estimators and test statistics. Semiparametric methods are highly demanding on software. Thus the presentation is completed by indicating the practical implementation in new version of the statistical computing environment XploRe.

Marlene Müller

[1] Sanford Weisberg,et al. ADAPTING FOR THE MISSING LINK , 1994 .

[2] T. Severini,et al. Quasi-Likelihood Estimation in Semiparametric Models , 1994 .

[3] Enno Mammen,et al. Testing Parametric Versus Semiparametric Modelling in Generalized Linear Models , 1996 .

[4] J. Hinde. XploRe: An Interactive Statistical Computing Environment , 1997 .

[5] Wolfgang Karl Härdle,et al. Nonparametric approaches to generalized linear models , 1992 .

[6] R. Tibshirani,et al. Generalized Additive Models , 1991 .

[7] Wolfgang Härdle,et al. Computerassisted Semiparametric Generalized Linear Models , 1997 .

[8] Joel L. Horowitz,et al. 2 Semiparametric and nonparametric estimation of quantal response models , 1993 .

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