IMPLICATIONS AND RELATIVE FIT OF SEVERAL 1ST-ORDER MARKOV-MODELS OF CONSUMER VARIETY SEEKING

We derive n-brand solutions for several first-order Markov models of c onsumer variety seeking, among them those of Givon (1984), Lattin and McAlister (1985) and several variants. Such solutions allow a comparat ive static analysis of long-run market shares relative to changes in t he models' parameters: variety-seeking intensity, brand preference and degree of feature sharing. Along with a simple Multinomial and a full y general first-order Markov model, these models are calibrated for co nsumers in a behavioral experiment. Such fits allow the nested models to be compared through a likelihood ratio test, and the non-nested one s to be compared through Hauser's (1978) U2 measure. These tests indic ate that the Lattin-McAlister model performs arguably better than all but the general Markov model.