Premium
Modeling Between‐Subject Variability in Decision Strategies via Statistical Clustering: A p ‐Median Approach
Author(s) -
Brown Nicholas,
Park Sanghyuk,
Steinley Douglas,
DavisStober Clintin P.
Publication year - 2018
Publication title -
journal of behavioral decision making
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.136
H-Index - 76
eISSN - 1099-0771
pISSN - 0894-3257
DOI - 10.1002/bdm.1957
Subject(s) - cluster analysis , computer science , a priori and a posteriori , exploratory data analysis , decision maker , cluster (spacecraft) , range (aeronautics) , data mining , subject (documents) , machine learning , artificial intelligence , exploratory research , operations research , mathematics , engineering , library science , philosophy , epistemology , sociology , anthropology , programming language , aerospace engineering
We present a statistical methodology for clustering decision makers according to similar choice behavior. We apply a p ‐median clustering algorithm that identifies an “exemplar” for each cluster, a decision maker who best represents that cluster. We demonstrate that information about group behavior can be inferred by examining the behavior of each cluster's exemplar. The method is exploratory, providing information about the prevalence of decision strategies without researchers needing to specify candidate strategies a priori. The method is also very general and can be applied to a wide range of decision‐making data structures. We illustrate our method by re‐analyzing two existing choice data sets. Copyright © 2016 John Wiley & Sons, Ltd.