skip navigation

PUBLICATIONS

Register for Latest Research

Stay Informed
Register with NCJRS to receive NCJRS's biweekly e-newsletter JUSTINFO and additional periodic emails from NCJRS and the NCJRS federal sponsors that highlight the latest research published or sponsored by the Office of Justice Programs.

NCJRS Abstract

The document referenced below is part of the NCJRS Virtual Library collection. To conduct further searches of the collection, visit the Virtual Library. See the Obtain Documents page for direction on how to access resources online, via mail, through interlibrary loans, or in a local library.

 

NCJ Number: 63806 Find in a Library
Title: DECREASING MULTICOLLINEARITY - A METHOD FOR MODELS WITH MULTIPLCATIVE FUNCTIONS
Journal: SOCIOLOGICAL METHODS AND RESEARCH  Volume:8  Issue:1  Dated:(AUGUST 1979)  Pages:35-56
Author(s): K W SMITH; M S SASAKI
Corporate Author: Sage Publications, Inc
United States of America
Date Published: 1979
Page Count: 22
Sponsoring Agency: Sage Publications, Inc
Thousand Oaks, CA 91320
Type: Report (Study/Research)
Format: Article
Language: English
Country: United States of America
Annotation: THIS SOCIOLOGICAL RESEARCH ARTICLE DESCRIBES A METHOD FOR DECREASING MULTICOLLINEARITY AMONG INDEPENDENT VARIABLES FOR MODELS WITH MULTIPLICATIVE FUNCTIONS.
Abstract: THE PROBLEMS CREATED BY MULTICOLLINEARITY AMONG THE INDEPENDENT VARIABLES IN LEAST-SQUARES REGRESSION ARE WELL-KNOWN. HOWEVER, WHEN THE MULTICOLLINEARITY AMONG THE INDEPENDENT VARIABLES IN A REGRESSION MODEL IS DUE TO A HIGH CORRELATION OF A MULTIPLICATIVE FUNCTION WITH ITS CONSTITUENT VARIABLES, THE MULTICOLLINEARITY CAN BE GREATLY REDUCED BY CENTERING THESE VARIABLES AROUND MINIMIZING CONSTANTS BEFORE FORMING THE MULTIPLICATIVE FUNCTION. THE VALUES OF THESE CONSTANTS THAT MINIMIZE THE MULTICOLLINEARITY ARE DERIVED, AND THE CONDITIONS ARE IDENTIFIED UNDER WHICH CENTERING THE VARIABLES ABOUT THEIR MEANS WILL REDUCE THE MULTICOLLINEARITY. AMONG THE ADVANTAGES OF THIS PROCEDURE ARE THAT THE MEAN SQUARE ERROR REMAINS AT ITS MINIMUM, THAT THE COEFFICIENTS FOR OTHER VARIABLES IN THE MODEL ARE UNAFFECTED BY IT, AND THAT THE ORDINARY LEAST-SQUARES ESTIMATES FOR THE ORIGINAL MODEL CAN BE CALCULATED FROM THOSE FOR THE MODIFIED MODEL. THUS, EVEN WHEN ESTIMATES OF THE ORIGINAL MODEL ARE DESIRED, THE PROCEDURE CAN BE USED TO REDUCE NUMERICAL ERROR. TABULAR DATA, NOTES, AND REFERENCES ARE INCLUDED. (AUTHOR ABSTRACT MODIFIED--MJW)
Index Term(s): Behavioral and Social Sciences; Evaluation; Evaluation techniques; Models; Research; Research methods; Sociology
To cite this abstract, use the following link:
http://www.ncjrs.gov/App/publications/abstract.aspx?ID=63806

*A link to the full-text document is provided whenever possible. For documents not available online, a link to the publisher's website is provided. Tell us how you use the NCJRS Library and Abstracts Database - send us your feedback.