Relationship between sums of squares in linear regression and semi-parametric regression


AYDIN D., ŞENEL B.

World Academy of Science, Engineering and Technology, vol.40, pp.6-10, 2009 (Scopus) identifier

  • Publication Type: Article / Article
  • Volume: 40
  • Publication Date: 2009
  • Journal Name: World Academy of Science, Engineering and Technology
  • Journal Indexes: Scopus
  • Page Numbers: pp.6-10
  • Keywords: Deviance, Penalized least, Residuals, Semi-parametric regression, Smoothing spline, Squares
  • Anadolu University Affiliated: Yes

Abstract

In this paper, the sum of squares in linear regression is reduced to sum of squares in semi-parametric regression. We indicated that different sums of squares in the linear regression are similar to various deviance statements in semi-parametric regression. In addition to, coefficient of the determination derived in linear regression model is easily generalized to coefficient of the determination of the semi-parametric regression model. Then, it is made an application in order to support the theory of the linear regression and semi-parametric regression. In this way, study is supported with a simulated data example.