Relaxing Measurement Invariance In Cross-National Consumer Research Using A Hierarchical IRT Model


Speaker


Abstract

With the growing interest of consumer researchers to test measures and theories in an international context, the cross-national invariance of instruments designed to measure consumer behavior constructs has become an important issue. Consumer researchers now routinely test for measurement invariance using confirmatory factor analytic (CFA) techniques before comparing countries on substantive issues. Yet at least two issues still need to be addressed. First, the ordinal nature of the rating scale is ignored, which has recently been shown to have deleterious effects on the validity of cross-national comparisons. Second, when few, or not items in CFA exhibit metric and scalar invariance across all countries, comparison of results across countries is difficult, if not impossible. We propose to solve these problems using a hierarchical item response theory measurement model. The model takes differential item functioning, including scale usage differences into account. Countries can be substantively compared, even in case of absence of cross-national measurement invariance. An empirical application is provided for consumer susceptibility to normative influence scale, using a sample of 5,484 respondents from 11 countries on four continents. Information: Dr. K. Gielens, kgielens@rsm.nl, ext. 4088635