About AMA

Executive Summary
Preference heterogeneity is a major research stream in marketing aimed at quantifying and understanding the diversity of demand for product attributes and attribute levels. In experimental settings in which consumers are presented with simple descriptions of product offerings, continuous distributions of heterogeneity, such as the multivariate normal, provide a useful representation of preference. However, in more complex cases in which respondents have value for only a few of the benefits associated with an offering or cognitive constraints that result in selective attention to a subset of the information available, continuous distributions of heterogeneity do not reflect the possibility that a subset of the variables have nonzero effect sizes for different respondents. Identifying which attributes are used in a brand choice decision is closely related to the statistical procedure of variable selection. This article extends variable selection methods to accommodate heterogeneity across consumers and data contexts, conditions that are frequently encountered in marketing studies. The authors apply the methods to a discrete choice conjoint study in which data are collected in both full-profile and partial-profile formats.

The empirical application demonstrates that the variable selection models result in better prediction and inference. The variable selection models had better out-of-sample fit, with a 6%–16% improvement in predictive accuracy. The results support the hypothesis that consumers adopt different decision strategies in different choice contexts. The study also shows that ignoring variable selection leads to biased parameter estimates and different conclusions about the importance of individual product attributes. These differences would result in different optimal product designs.

Biography
Timothy J. Gilbride is Assistant Professor of Marketing in the Mendoza College of Business at University of Notre Dame. Tim’s research interests focus on the application of Bayesian statistical methods to investigate marketing problems. His work has appeared or is forthcoming in Marketing Science, Marketing Letters, Quantitative Marketing and Economics, and Journal of Marketing Research. Tim obtained his PhD from Ohio State University in 2004. He teaches marketing research at the undergraduate and MBA levels at Notre Dame. Tim’s professional experience includes consulting and staff positions in various industries, including profit and not-for-profit firms.

Greg M. Allenby is Helen C. Kurtz Chair in Marketing in the Fisher College of Business at Ohio State University. Greg’s research focuses on quantitative aspects of marketing, including the development and application of Bayesian statistical methods. He is a Fellow of the American Statistical Association and is coauthor of Bayesian Statistics and Marketing (John Wiley & Sons 2005). Greg is an associate editor for Marketing Science, Journal of Business and Economic Statistics, and Quantitative Marketing and Economics. He is also on the editorial boards of Journal of Marketing Research and Marketing Letters. Within the American Marketing Association, Greg has served as vice president of the Research Council and has chaired the Advanced Research Technique Forum, a national conference that brings together quantitative researchers from industry and academe. Within the American Statistical Association, he has served as chair of the Section on Statistics in Marketing. He has authored numerous publications that have appeared in leading marketing and statistics journals.

Jeff D. Brazell is President and Chief Executive Officer it The Modellers LLC. Jeff brings a rich blend of management and marketing experience to his academic research. Over the past 20 years, he has been extensively involved in advanced predictive modeling and market research and has taught at two universities. Before pursuing his PhD, Jeff had multifaceted business experience, serving as a vice president at a service company, vice president of an international trade company, and president of a software development firm. He received his PhD from the University of Sydney. Jeff’s primary research interests include quantitative analysis of consumer behavior, including choice modeling methods, return-on-investment models in marketing, and application of quantitative methods to strategy decisions. Jeff’s recent industry consulting experience includes modeling projects for companies such as American Express, Boeing, Citibank, Disney, General Electric, General Motors, IBM, Intel, Microsoft, NCR, Pfizer, Sony, Toyota, and Verizon.

Member Comments (0):

To rate or comment on articles, you must be a logged in AMA member. Click here to join