PERFORMANCE OF THE INTEGRATED RANDOM-COEFFICIENTS COVARIANCE PROBIT MODEL - IMPLICATIONS FOR BRAND CHOICE

In probit brand choice models, researchers increasingly focus on rando m variation of key parameters of interest. An important source of such variation may be due to differing consumer response to marketing effo rts across purchase occasions, Also, variables common across alternati ves influence purchase behavior, but may not be measured. Failure to a dequately control for both these factors may cause biased estimates. M ore importantly, the incorrect estimates may lead to erroneous manager ial conclusions. While either problem can be directly addressed in a ( non-independent) probit model, we focus on whether a joint specificati on of both factors is necessary. We highlight the potential for mislea ding managerial inferences by contrasting the model with both sources of variation against nested models, using empirical data on ketchup pr oduct category. Further, in a simulation study we establish the extent of bias in recovery of parameters due to different specifications of both factors. (C) 1998 Elsevier Science B.V.