Addressing Preference Heterogeneity, Multiple Scales and Attribute Attendance with a Correlated Finite Mixing Model of Tap Water Choice.

Unobserved heterogeneity of error scale in choice models is a recent extension of the better investigated issue of heterogeneity of taste intensity. It is achieved by fitting choice panel data with specifications that simultaneously handle inter-personal variation in scale and taste. The aim is to separate differences in preference intensities across respondents from differences in the degree of consistency in choice behaviour, or 'preference discrimination', while accounting for correlation between the two. Another recent substantive issue in choice data analysis is attribute non-attendance. We develop a finite mixing model to address simultaneously the three issues above. We empirically prove the concept on stated preference data related to tap water attributes in a study for industry regulation. [ABSTRACT FROM AUTHOR]