Some new diagnostics of multicollinearity in linear regression model

The problem of multicollinearity compromises the numerical stability of the regression coefficient estimate and cause some serious problem in validation and interpretation of the model. In this paper, we propose two new collinearity diagnostics for the detection of collinearity among regressors, bas...

Full description

Bibliographic Details
Main Authors:	Ullah, Muhammad Imdad, Aslam, Muhammad, Altaf, Saima, Ahmed, Munir
Format:	Article
Language:	English
Published:	Penerbit Universiti Kebangsaan Malaysia 2019
Online Access:	http://journalarticle.ukm.my/14359/ http://journalarticle.ukm.my/14359/ http://journalarticle.ukm.my/14359/1/26%20Muhammad%20Imdad%20Ullah.pdf

id	ukm-14359
recordtype	eprints
spelling	ukm-143592020-03-03T08:18:38Z http://journalarticle.ukm.my/14359/ Some new diagnostics of multicollinearity in linear regression model Ullah, Muhammad Imdad Aslam, Muhammad Altaf, Saima Ahmed, Munir The problem of multicollinearity compromises the numerical stability of the regression coefficient estimate and cause some serious problem in validation and interpretation of the model. In this paper, we propose two new collinearity diagnostics for the detection of collinearity among regressors, based on coefficient of determination and adjusted coefficient of determination from auxiliary regression of regressors. A Monte Carlo simulation study has been conducted to compare the existing and proposed collinearity diagnostic tests. Comparison of diagnostics on some existing collinear data are also made. Penerbit Universiti Kebangsaan Malaysia 2019-09 Article PeerReviewed application/pdf en http://journalarticle.ukm.my/14359/1/26%20Muhammad%20Imdad%20Ullah.pdf Ullah, Muhammad Imdad and Aslam, Muhammad and Altaf, Saima and Ahmed, Munir (2019) Some new diagnostics of multicollinearity in linear regression model. Sains Malaysiana, 48 (9). pp. 2051-2060. ISSN 0126-6039 http://www.ukm.my/jsm/malay_journals/jilid48bil9_2019/KandunganJilid48Bil9_2019.html
repository_type	Digital Repository
institution_category	Local University
institution	Universiti Kebangasaan Malaysia
building	UKM Institutional Repository
collection	Online Access
language	English
description	The problem of multicollinearity compromises the numerical stability of the regression coefficient estimate and cause some serious problem in validation and interpretation of the model. In this paper, we propose two new collinearity diagnostics for the detection of collinearity among regressors, based on coefficient of determination and adjusted coefficient of determination from auxiliary regression of regressors. A Monte Carlo simulation study has been conducted to compare the existing and proposed collinearity diagnostic tests. Comparison of diagnostics on some existing collinear data are also made.
format	Article
author	Ullah, Muhammad Imdad Aslam, Muhammad Altaf, Saima Ahmed, Munir
spellingShingle	Ullah, Muhammad Imdad Aslam, Muhammad Altaf, Saima Ahmed, Munir Some new diagnostics of multicollinearity in linear regression model
author_facet	Ullah, Muhammad Imdad Aslam, Muhammad Altaf, Saima Ahmed, Munir
author_sort	Ullah, Muhammad Imdad
title	Some new diagnostics of multicollinearity in linear regression model
title_short	Some new diagnostics of multicollinearity in linear regression model
title_full	Some new diagnostics of multicollinearity in linear regression model
title_fullStr	Some new diagnostics of multicollinearity in linear regression model
title_full_unstemmed	Some new diagnostics of multicollinearity in linear regression model
title_sort	some new diagnostics of multicollinearity in linear regression model
publisher	Penerbit Universiti Kebangsaan Malaysia
publishDate	2019
url	http://journalarticle.ukm.my/14359/ http://journalarticle.ukm.my/14359/ http://journalarticle.ukm.my/14359/1/26%20Muhammad%20Imdad%20Ullah.pdf
first_indexed	2023-09-18T20:06:55Z
last_indexed	2023-09-18T20:06:55Z
_version_	1777407220085948416

Some new diagnostics of multicollinearity in linear regression model

Similar Items