MDL mean function selection in semiparametric Kernel regression models

Jan G. de Gooijer; Ao Yuan

We study the problem of selecting the optimal functional form among a set of non-nested nonlinear mean functions for a semiparametric kernel based regression model. To this end we consider Rissanen's minimum description length (MDL) principle. We prove the consistency of the proposed MDL criterion. Its performance is examined via simulated data sets of univariate and bivariate nonlinear regression models.

MoreLess

Year of publication:	2008 ; Forthcoming in: Communications in Statistics: Theory and Methods, 2008
Authors:	Gooijer, Jan G. de ; Yuan, Ao
Publisher:	Rotterdam [u.a.] : Tinbergen Inst.
Subject:	Kernel density estimator \| Maximum likelihood estimator \| Minimum description length \| Nonlinear regression \| Semiparametric model \| Nichtparametrisches Verfahren \| Nonparametric statistics \| Schätztheorie \| Estimation theory \| Regressionsanalyse \| Regression analysis \| Maximum-Likelihood-Schätzung \| Maximum likelihood estimation \| Nichtlineare Regression