Template-Type: ReDIF-Paper 1.0
Series: Tinbergen Institute Discussion Papers
Creation-Date: 2008-05-07
Number: 08-046/4
Author-Name: Jan G. De Gooijer
Author-Email: j.g.degooijer@few.eur.nl
Author-Workplace-Name: University of Amsterdam
Author-Name: Ao Yuan
Author-Email: ayuan@howard.edu
Author-Workplace-Name: Howard University, Washington DC, USA
Title: MDL Mean Function Selection in Semiparametric Kernel Regression Models
Abstract: 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.
Classification-JEL: C14
Keywords: Kernel density estimator; Maximum likelihood estimator; Minimum description length; Nonlinear regression; Semiparametric model
File-Url: https://papers.tinbergen.nl/08046.pdf
File-Format: application/pdf
File-Size: 255791 bytes
Handle: RePEc:tin:wpaper:20080046