Evaluating the appropriateness of using multivariate techniques in studies of consumer behavior in the theses and dissertations of two higher education institutions

Abstract

This paper is part of a large study to assess the appropriateness of using multivariate statistical techniques in the theses and dissertations of two institutions of higher education in the field of marketing and as regards consumer behavior, from 1997 to 2006. This paper focuses on 11 multivariate techniques (regression analysis, discriminant analysis, logistic regression analysis, canonical correlation, multivariate analysis of variance, conjoint analysis, structural equation modeling, factor analysis, cluster analysis, correspondence analysis, and multidimensional scaling) that show great potential for use in marketing studies. The objective of this study was to analyze whether applying these techniques suits the needs of the research problem at the core of these theses and dissertations, as well as to evaluate to what extent they fulfill their premises. Overall, the results suggest that researchers should be more committed to checking all the theoretical precepts that underlie the application of these multivariate techniques.