Parameter bias from unobserved effects in the multinomial logit model of consumer choice

Over the past two decades, validation of choice models has focused on predi ctive validity rather than parameter bias. In real-world validation of choi ce models, true parameter values are unknown, so examination of parameter b ias is not possible. In contrast, the main focus of this study is parameter bias in simulated scanner-panel choice data with known parameter values. S tudy of parameter bias enables the assessment of a fundamental issue not ad dressed in the choice modeling literature-the extent to which the logit cho ice model is capable of distinguishing unobserved effects that give rise to persistence in observed choices (e,g., heterogeneity and state dependence) . Although econometric theory provides some information about the causes of bias, the extent of such bias in typical scanner data applications remains unclear. The authors present an extensive simulation study that provides i nformation on the extent of bias resulting from the misspecification of fou r unobserved effects that receive frequent attention in the literature-choi ce set effects, heterogeneity in preferences and market response, state dep endence, and serial correlation. The authors outline implications for model builders and managers. In general, the potential for parameter bias in cho ice model applications appears to be high. Overall, a logit model with choi ce set effects and the Guadagni-Little loyalty variable produces the most v alid parameter estimates.