A New Measure of Predictor Variable Importance in Multiple Regression

Journal of Marketing Research 15(3), 356-360, 1978

5 Pages Posted: 21 Feb 2016

See all articles by Wayne S. DeSarbo

Wayne S. DeSarbo

Pennsylvania State University

Paul E. Green

University of Pennsylvania, The Wharton School, Marketing Department (Deceased)

J. Carroll

Rutgers, The State University of New Jersey (Deceased)

Date Written: 1978

Abstract

Ambiguity surrounds any importance measure in cases in which predictor variables are correlated. However, a new measure is proposed that has attractive properties, such as providing individual contributions that are both non-negative and sum to R2. The new measure is compared with four other commonly used measures and its advantages over each of them are pointed out.

Suggested Citation

DeSarbo, Wayne S. and Green, Paul E. and Carroll, J., A New Measure of Predictor Variable Importance in Multiple Regression (1978). Journal of Marketing Research 15(3), 356-360, 1978, Available at SSRN: https://ssrn.com/abstract=2735113

Wayne S. DeSarbo (Contact Author)

Pennsylvania State University ( email )

University Park
State College, PA 16802
United States

Paul E. Green

University of Pennsylvania, The Wharton School, Marketing Department (Deceased) ( email )

700 Jon M. Huntsman Hall
3730 Walnut Street
Philadelphia, PA 19104-6340
United States

J. Carroll

Rutgers, The State University of New Jersey (Deceased)

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
16
Abstract Views
234
PlumX Metrics