A weighted stochastic restricted ridge estimator in partially linear model

ABSTRACT

In this article, we consider the estimation of a partially linear model when stochastic linear restrictions on the parameter components are assumed to hold. Based on the weighted mixed estimator, profile least-squares method, and ridge method, a weighted stochastic restricted ridge estimator of the parametric component is introduced. The properties of the new estimator are also discussed. Finally, a simulation study is given to show the performance of the new estimator.

KEYWORDS:

• Multicollinearity
• Partially linear model
• Profile least-squares approach
• Stochastic linear restrictions
• Weighted mixed estimator.

MATHEMATICS SUBJECT CLASSIFICATION:

• Primary 62J05, 62J07

Acknowledgments

The author is highly obliged to the editor and the reviewer for the comments and suggestions which improved the article in its present form.

Funding

This work was supported by the National Natural Science Foundation of China (Nos. 11501072).