Cover Image

Penalized regression method in high dimensional data

In huge multivariate data set with a number of variables greater than the number of samples, the standard linear model (or ordinary least squares method) performs badly. In such situations, a better option is penalized regression, which allows you to design a linear regression model that is penalize...

Full description

Saved in:
Bibliographic Details
Main Authors: Jaafar, Zuharah, Ismail, Norazlina
Format: Article
Published: Little Lion Scientific 2022
Subjects:
QA Mathematics
Online Access:http://eprints.utm.my/id/eprint/98757/
http://www.jatit.org/volumes/Vol100No8/9Vol100No8.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.utm.98757
record_format eprints
spelling my.utm.987572023-02-02T08:25:38Z http://eprints.utm.my/id/eprint/98757/ Penalized regression method in high dimensional data Jaafar, Zuharah Ismail, Norazlina QA Mathematics In huge multivariate data set with a number of variables greater than the number of samples, the standard linear model (or ordinary least squares method) performs badly. In such situations, a better option is penalized regression, which allows you to design a linear regression model that is penalized for having too many variables by adding a constraint to the equation Shrinkage or regularization procedures are other names for this. The penalty has the effect of reducing (i.e. shrinking) the coefficient values towards zero. This permits the coefficients of the less important variables to be near to or equal to zero. By decreasing the number of coefficients and maintaining those with coefficients greater than zero, penalized regression models improve prediction in new data when compared to traditional methods. We demonstrate that the proposed regularizer is capable of achieving competitive results as well as exceedingly compact networks. Extensive tests are carried out on a number of benchmark datasets to demonstrate the effectiveness of the method. Little Lion Scientific 2022 Article PeerReviewed Jaafar, Zuharah and Ismail, Norazlina (2022) Penalized regression method in high dimensional data. Journal of Theoretical and Applied Information Technology, 100 (8). pp. 2470-2479. ISSN 1992-8645 http://www.jatit.org/volumes/Vol100No8/9Vol100No8.pdf
institution Universiti Teknologi Malaysia
building UTM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknologi Malaysia
content_source UTM Institutional Repository
url_provider http://eprints.utm.my/
topic QA Mathematics
spellingShingle QA Mathematics
Jaafar, Zuharah
Ismail, Norazlina
Penalized regression method in high dimensional data
description In huge multivariate data set with a number of variables greater than the number of samples, the standard linear model (or ordinary least squares method) performs badly. In such situations, a better option is penalized regression, which allows you to design a linear regression model that is penalized for having too many variables by adding a constraint to the equation Shrinkage or regularization procedures are other names for this. The penalty has the effect of reducing (i.e. shrinking) the coefficient values towards zero. This permits the coefficients of the less important variables to be near to or equal to zero. By decreasing the number of coefficients and maintaining those with coefficients greater than zero, penalized regression models improve prediction in new data when compared to traditional methods. We demonstrate that the proposed regularizer is capable of achieving competitive results as well as exceedingly compact networks. Extensive tests are carried out on a number of benchmark datasets to demonstrate the effectiveness of the method.
format Article
author Jaafar, Zuharah
Ismail, Norazlina
author_facet Jaafar, Zuharah
Ismail, Norazlina
author_sort Jaafar, Zuharah
title Penalized regression method in high dimensional data
title_short Penalized regression method in high dimensional data
title_full Penalized regression method in high dimensional data
title_fullStr Penalized regression method in high dimensional data
title_full_unstemmed Penalized regression method in high dimensional data
title_sort penalized regression method in high dimensional data
publisher Little Lion Scientific
publishDate 2022
url http://eprints.utm.my/id/eprint/98757/
http://www.jatit.org/volumes/Vol100No8/9Vol100No8.pdf
_version_ 1758578015325913088
score 13.211869

Similar Items