Performance of the difference-based estimators in partially linear models

Abstract

In this paper, we consider a commonly used partially linear model. We proposed a restricted difference-based ridge estimator for the vector of parameters β in a partially linear model with one smoothing term when additional linear restrictions on the parameter vector are assumed to hold. The ideas in the paper are illustrated in a real data set and in a Monte Carlo simulation study.

Keywords:

• difference-based ridge regression estimator
• differencing matrix
• Lagrangian function
• partially linear model

AMS Subject Classification :

• Primary: 62G08
• Secondary: 62J05
• 62J07

Acknowledgements

The author is grateful to the editor and the referee for valuable comments which improved an earlier draft of this article.