Models of Sequential Evaluation in Best-Worst Choice Tasks
Tatiana Dyachenko, Rebecca Walker Reczek, Greg M. Allenby (2014) Models of Sequential Evaluation in Best-Worst Choice Tasks. Marketing Science 33(6):828-848. doi.org/10.1287/mksc.2014.0870
Posted: 2 Jun 2012 Last revised: 19 Jan 2015
Date Written: June 2, 2012
We examine the nature of best-worst data for modeling consumer preferences and predicting their choices. We show that, contrary to the assumption of widely used models, the best and worst responses do not originate from the same data-generating process. We propose a sequential evaluation model and show that later choices have systematically larger coeﬃcients as compared to earlier choices. We also ﬁnd the presence of an elicitation eﬀect that leads to larger coeﬃcients when respondents are asked to select the worst alternative, meaning that respondents are surer about what they like least than what they like most. Finally, we investigate global inference retrieval in choice tasks, which can be represented by the central limit theorem and normally distributed errors, versus episodic retrieval represented by extreme value errors. We ﬁnd that both speciﬁcations of the error term are plausible and advise to use the proposed sequential logit model for practical reasons. We apply our model to data from a national survey investigating the concerns associated with hair care. We ﬁnd that accounting for the sequential evaluation in the best-worst tasks and the presence of the scaling eﬀects leads to diﬀerent managerial implications compared to the results from currently used models.
Keywords: Bayesian estimation, psychological models, choice models
JEL Classification: C11, C25, M31
Suggested Citation: Suggested Citation