Assessing regression-based importance weights for quality perceptions and satisfaction judgements in the presence of higher order and/orinteraction effects

Abstract

The quest for a better understanding of how consumers ' quality perceptions and satisfaction judgements contribute to ultimate purchase intentions continues to represent one of the key challenges facing service marketers. Using regression models the traditional approach is to employ direct measures of these constructs to identify the additive contributions of quality perceptions and satisfaction judgments as independent variables to consumers' stated future purchase intentions as a dependent variable. This study demonstrates that unobserved potential higher-order factors (and their interactions) in such efforts can lead to problems associated with interpreting regression coefficients as importance weights. A framework is proposed and empirically validated in a multiindustry study, to assist service marketers in identifying potential higher-order factors and their interactions in their own models of consumer decision-making in service settings. The managerial and research implications of the study are presented and discussed.