A FACTOR-ANALYTIC PROBIT MODEL FOR REPRESENTING THE MARKET-STRUCTURE IN PANEL-DATA

Internal market structure analysis infers both brand attributes and co nsumer preferences for those attributes from preference or choice data . The authors exploit a new method for estimating probit models from p anel data to infer market structures that can be displayed in few dime nsions, even though the model can represent every possible vector of p urchase probabilities. The result outperforms each of several other mo dels, including Choice Map, SCULPTRE, and Chintagunta's latent class m odel in terms of goodness of fit, predictive validity, and face validi ty for a detergent data set. Because theirs is the only market structu re model to outperform the structureless Dirichlet-multinomial stochas tic brand choice model, the other methods cannot claim to have recover ed market structure for these data.