Comparing three methods of handling multicollinearity using simulation approach

In regression, the objective is to explain the variation in one or more response variables, by associating this variation with proportional variation in one or more explanatory variables. A frequent obstacle is that several of the explanatory variables will vary in rather similar ways. This phenomen...

Full description

Saved in:

Bibliographic Details
Main Author:	Adnan, Norliza
Format:	Thesis
Language:	English
Published:	2006
Subjects:	QA Mathematics
Online Access:	http://eprints.utm.my/id/eprint/5335/1/NorlizaAdnanMFS2006.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-utm-ep.5335
record_format	uketd_dc
spelling	my-utm-ep.53352018-03-07T20:57:32Z Comparing three methods of handling multicollinearity using simulation approach 2006-05 Adnan, Norliza QA Mathematics In regression, the objective is to explain the variation in one or more response variables, by associating this variation with proportional variation in one or more explanatory variables. A frequent obstacle is that several of the explanatory variables will vary in rather similar ways. This phenomenon called multicollinearity, is a common problem in regression analysis. Handling multicollinearity problem in regression analysis is important because least squares estimations assume that predictor variables are not correlated with each other. The performances of ridge regression (RR), principal component regression (PCR) and partial least squares regression (PLSR) in handling multicollinearity problem in simulated data sets are compared to help and give future researchers a comprehensive view about the best procedure to handle multicollinearity problems. PCR is a combination of principal component analysis (PCA) and ordinary least squares regression (OLS) while PLSR is an approach similar to PCR because a component that can be used to reduce the number of variables need to be constructed. RR on the other hand is the modified least square method that allows a biased but more precise estimator. The algorithm is described and for the purpose of comparing the three methods, simulated data sets where the number of cases was less than the number of observations were used. The goal was to develop a linear equation that relates all the predictor variables to a response variable. For comparison purposes, mean square errors (MSE) were calculated. A Monte Carlo simulation study was used to evaluate the effectiveness of these three procedure. The analysis including all simulations and calculations were done using statistical package S-Plus 2000 software. 2006-05 Thesis http://eprints.utm.my/id/eprint/5335/ http://eprints.utm.my/id/eprint/5335/1/NorlizaAdnanMFS2006.pdf application/pdf en public masters Universiti Teknologi Malaysia, Faculty of Science Faculty of Science
institution	Universiti Teknologi Malaysia
collection	UTM Institutional Repository
language	English
topic	QA Mathematics
spellingShingle	QA Mathematics Adnan, Norliza Comparing three methods of handling multicollinearity using simulation approach
description	In regression, the objective is to explain the variation in one or more response variables, by associating this variation with proportional variation in one or more explanatory variables. A frequent obstacle is that several of the explanatory variables will vary in rather similar ways. This phenomenon called multicollinearity, is a common problem in regression analysis. Handling multicollinearity problem in regression analysis is important because least squares estimations assume that predictor variables are not correlated with each other. The performances of ridge regression (RR), principal component regression (PCR) and partial least squares regression (PLSR) in handling multicollinearity problem in simulated data sets are compared to help and give future researchers a comprehensive view about the best procedure to handle multicollinearity problems. PCR is a combination of principal component analysis (PCA) and ordinary least squares regression (OLS) while PLSR is an approach similar to PCR because a component that can be used to reduce the number of variables need to be constructed. RR on the other hand is the modified least square method that allows a biased but more precise estimator. The algorithm is described and for the purpose of comparing the three methods, simulated data sets where the number of cases was less than the number of observations were used. The goal was to develop a linear equation that relates all the predictor variables to a response variable. For comparison purposes, mean square errors (MSE) were calculated. A Monte Carlo simulation study was used to evaluate the effectiveness of these three procedure. The analysis including all simulations and calculations were done using statistical package S-Plus 2000 software.
format	Thesis
qualification_level	Master's degree
author	Adnan, Norliza
author_facet	Adnan, Norliza
author_sort	Adnan, Norliza
title	Comparing three methods of handling multicollinearity using simulation approach
title_short	Comparing three methods of handling multicollinearity using simulation approach
title_full	Comparing three methods of handling multicollinearity using simulation approach
title_fullStr	Comparing three methods of handling multicollinearity using simulation approach
title_full_unstemmed	Comparing three methods of handling multicollinearity using simulation approach
title_sort	comparing three methods of handling multicollinearity using simulation approach
granting_institution	Universiti Teknologi Malaysia, Faculty of Science
granting_department	Faculty of Science
publishDate	2006
url	http://eprints.utm.my/id/eprint/5335/1/NorlizaAdnanMFS2006.pdf
_version_	1747814582498361344

Comparing three methods of handling multicollinearity using simulation approach

Similar Items