SILPAKORN UNIVERSITY SCIENCE AND TECHNOLOGY JOURNAL, Vol 6, No 1 (2012)

The Estimation of Smoothing Parameter using Smoothing Techniques on Nonparametric Regression

Autcha Araveeporn

Department of Applied Statistics, Faculty of Science, King Monkut’s Institute of Technology Ladkrabang


Abstract


This article discusses on the smoothing parameter which is controlled by interpolating spline based on the smoothing techniques that consisted of smoothing spline method, kernel regression method, and penalized spline regression method.
The smoothing parameter is controlled the fitting model and the trade of between the bias of the estimator. We also propose the range of smoothing parameter of these methods to fit the smoothing function which data is nonlinear. Therefore, we mention the characteristic of smoothing function when the smoothing parameters have the various values. According to the results, it is concluded that the smoothing parameter of the smoothing spline method is suitable worked between zero to one, the kernel regression is good performance between two to ten, and the penalized spline is useful between one to ten.

Key Words : Smoothing Parameter; Smoothing Technique; Smoothing Spline; Kernel Regression; Penalized Spline Regression

Full Text: PDF