“…For examples, see the special issue of the Journal of Econometrics (1993, v. 58, July, p. 1-274) and Marketing Letters (1994, v. 5Ϻ4, p. 335-350). However, all empirical studies are limited to a binary response variable, and even many theoretical developments tend to focus on binary response models, as described in Horowitz et al (1994). (c) Semiparametric II: While correct specification of a random component is important for consistent estimation of systematic utility, response shape of systematic utility could suggest interesting behavioral implications.…”