A Convex Combination Method of Subset Selection Criterion in a Linear Regression

  • Unique Paper ID: 166969
  • Volume: 11
  • Issue: 3
  • PageNo: 113-118
  • Abstract:
  • In multiple linear regression analysis, problem multicollinearity and outliers are the two serious issues. Due to these problems, the ordinary least squares(OLS) method does not yield good estimates to the regression parameters. When such a situation arise, there are various methods to estimate the optimum estimates to the regression parameters and one such is called subset selection methods. Several authors have been suggested various modes of subset selection methods based on OLS methods, which are sensitive to multicollinearity, heteroscadesticity, non-normal error distribution, etc. In order to overcome the problem of these factors, here we suggest a new method of obtaining the good estimates to the regression parameters by selecting a good subset model, and we called it as Weighted Method of Subset Selection Criteria. It is obtained by shrinking the GSp and MGSp criterions using convex combination concepts. The performance of the suggested criteria is evaluated empirically and compared with some of the existing methods of subset selection criterions. Empirical results indicate that the proposed criteria performs better in presence of both multicollinearity and outliers.

Copyright & License

Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

BibTeX

@article{166969,
        author = {SATISH BHAT},
        title = {A Convex Combination Method of Subset Selection Criterion in a Linear Regression},
        journal = {International Journal of Innovative Research in Technology},
        year = {2024},
        volume = {11},
        number = {3},
        pages = {113-118},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=166969},
        abstract = {In multiple linear regression analysis, problem multicollinearity and outliers are the two serious issues. Due to these problems, the ordinary least squares(OLS) method does not yield good estimates to the regression parameters.  When such a situation arise, there are various methods to estimate the optimum estimates to the regression parameters and one such is called subset selection methods. Several authors have been suggested various modes of subset selection methods based on OLS methods, which are sensitive to multicollinearity, heteroscadesticity, non-normal error distribution, etc. In order to overcome the problem of these factors, here we suggest a new method of obtaining the good estimates to the regression parameters by selecting a good subset model, and we called it as Weighted Method of Subset Selection Criteria. It is obtained by shrinking the GSp and MGSp criterions using convex combination concepts. The performance of the suggested criteria is evaluated empirically and compared with some of the existing methods of subset selection criterions. Empirical results indicate that the proposed criteria performs better in presence of both multicollinearity and outliers.},
        keywords = {Multiple linear regression, multicollinearity, outliers, subset selection, ridge estimator.},
        month = {August},
        }

Cite This Article

  • ISSN: 2349-6002
  • Volume: 11
  • Issue: 3
  • PageNo: 113-118

A Convex Combination Method of Subset Selection Criterion in a Linear Regression

Related Articles