Measurement properties of rankings and ratings
Ratings are the dominant approach to construct measurement in the social and behavioral sciences, including the applied business disciplines. The literature documents problems with the use of ratings, but workable alternatives are few. This paper proposes the use of rankings for construct measurement. Rankings and ratings are systematically evaluated using multitrait–multimethod (MTMM) structural equations modeling. MTMM models partition the variation in measures into trait, method, and error components. The assessment presented here favors rankings for construct measurement for the brand context studied. The analysis presents a test of the brand signaling model that Erdem and Swait (1998) propose.
When requesting a correction, please mention this item's handle: RePEc:eee:jbrese:v:64:y:2011:i:12:p:1296-1302. See general information about how to correct material in RePEc.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: (Zhang, Lei)
If references are entirely missing, you can add them using this form.