Open AccessPredicted preference conjoint analysis
Author(s) -
Sonja Radas,
Dražen Prelec
Publication year - 2021
Publication title -
plos one
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.99
H-Index - 332
ISSN - 1932-6203
DOI - 10.1371/journal.pone.0256010
Subject(s) - conjoint analysis , preference , context (archaeology) , polling , argument (complex analysis) , preference elicitation , ask price , revealed preference , social psychology , psychology , marketing , computer science , econometrics , data science , economics , microeconomics , medicine , business , economy , operating system , paleontology , biology
In this paper we propose a new method of eliciting market research information. Instead of asking respondents for their personal choices and preferences, we ask respondents to predict the choices of other respondents to the survey. Such predictions tap respondents’ knowledge of peers, whether based on direct social contacts or on more general cultural information. The effectiveness of this approach has already been demonstrated in the context of political polling. Here we extend it to market research, specifically, to conjoint analysis. An advantage of the new approach is that it can elicit reliable responses in situations where people are not comfortable with disclosing their true preferences, but may be willing to give information about people around them. A theoretical argument demonstrates that predictions should yield utility estimates that are more accurate. These theoretical results are confirmed in four online experiments.