Ridge estimation of a semiparametric regression model

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.