×

A stochastic restricted ridge regression estimator in partially linear varying coefficient models. (Chinese. English summary) Zbl 1399.62122

Summary: As a generalization of varying coefficient model and partially linear model, partially linear varying coefficient model has attracted more and more attention in recent years. This paper considers estimation of the semiparametric model when the covariates in the linear part are suffered with multi-collinearity and some additional stochastic linear restrictions on the parametric component are available. Based on the profile least-squares approach, ridge regression and mixed regression method, we propose a profile mixed estimator for the parametric component, and give its asymptotic properties. Finally, some simulation studies are conducted to illustrate the proposed procedure and the results are satisfactory.

MSC:

62J07 Ridge regression; shrinkage estimators (Lasso)
62G05 Nonparametric estimation
62J12 Generalized linear models (logistic models)
PDFBibTeX XMLCite