Ridge estimation of a semiparametric regression model

https://doi.org/10.1016/j.cam.2004.07.032Get rights and content
Under an Elsevier user license
open archive

Abstract

Considered the semiparametric regression model li=AiTX+s(ti)+Δi(i=1,2,,n).Firstly, ridge estimators of both parameters and nonparameters are attained without a restrained design matrix. Secondly, the ridge estimator will be compared with two steps estimation under a mean square error and some conditions in which the former excels the latter are given. Finally, the validity and feasibility of the method are illustrated by a simulating example.

Keywords

Semiparametric regression model
Ridge estimation
Two steps estimation
Mean square error

Cited by (0)

Supported by National Natural Science Foundation of China (No. 40274005), and Big Item of Education Office, Hubei Province (No. 2001Z06003).