International Conference on Advanced Technologies, Computer Engineering and Science

Choosing optimal truncation level on estimation of the nonparametric regression with Padé approximation

D. Aydin E. YILMAZ

Abstract

In this paper, Padé approximation based on truncated total least squares method (P-TTLS) is defined as a nonparametric method to estimate the nonparametric regression model and to obtain an optimal estimation, determination of the truncation level is illustrated. Here, three selection method are used for choosing the truncation level which are GCV, AICc and REML respectively. To compare and interpreting the performances of the criteria, a simulation study is carried out and results are presented.



Conference
International Conference on Advanced Technologies, Computer Engineering and Science
Keywords
Nonparametric regression Padé approximation truncation level

Language
English

Subject
Computer Science

Full Paper (PDF)

445 views
320 downloads