An Elimination by Aspects Model of Consumer Response to Promotion Calibrated on UPC Scanner Data

Abstract

Because consumers are believed to use simplifying heuristics to screen alternatives before choosing one to purchase, the authors formulate and estimate an elimination by aspects model at the individual household level, using UPC scanner data collected from purchases of regular ground coffee. The proposed model fits and predicts the data as well as its compensatory approximation. The parameters of the proposed model are reasonably stable, unbiased, and different in interesting ways from their compensatory counterparts.