A Comparison of Segment Retention Criteria for Finite Mixture Logit Models

Despite the widespread application of finite mixture models in marketing research, the decision of how many segments to retain in the models is an important unresolved issue. Almost all applications of the models in marketing rely on segment retention criteria such as Akaike's information criterion, Bayesian information criterion, consistent Akaike's information criterion, and information complexity to determine the number of latent segments to retain. Because these applications employ real-world data in which the true number of segments is unknown, it is not clear whether these criteria are effective. Retaining the true number of segments is crucial because many product design and marketing decisions depend on it. The purpose of this extensive simulation study is to determine how well commonly used segment retention criteria perform in the context of simulated multinomial choice data, as obtained from supermarket scanner panels, in which the true number of segments is known. The authors find that an Akaike's information criterion with a penalty factor of three rather than the traditional value of two has the highest segment retention success rate across nearly all experimental conditions. Currently, this criterion is rarely, if ever, applied in the marketing literature. Experimental factors of particular interest in marketing contexts, such as the number of choices per household, the number of choice alternatives, the error variance of the choices, and the minimum segment size, have not been considered in the statistics literature. The authors show that they, among other factors, affect the performance of segment retention criteria.

[1]  A. Hope.  A Simplified Monte Carlo Significance Test Procedure , 1968 .

[2]  Paul I. Feder,et al.  On the Distribution of the Log Likelihood Ratio Test Statistic When the True Parameter is "Near" the Boundaries of the Hypothesis Regions , 1968 .

[3]  H. Akaike,et al.  Information Theory and an Extension of the Maximum Likelihood Principle , 1973 .

[4]  G. Schwarz.  Estimating the Dimension of a Model , 1978 .

[5]  Hamparsum Bozdogan.  MULTI-SAMPLE CLUSTER ANALYSIS AND APPROACHES TO VALIDITY STUDIES IN CLUSTERING INDIVIDUALS. , 1981 .

[6]  Murray Aitkin,et al.  Statistical Modelling of Data on Teaching Styles , 1981 .

[7]  David C. Schmittlein,et al.  A Bayesian Cross-Validated Likelihood Method for Comparing Alternative Specifications of Quantitative Models , 1985 .

[8]  G. McLachlan.  On Bootstrapping the Likelihood Ratio Test Statistic for the Number of Components in a Normal Mixture , 1987 .

[9]  H. Bozdogan.  Model selection and Akaike's Information Criterion (AIC): The general theory and its analytical extensions , 1987 .

[10]  Geoffrey J. McLachlan,et al.  Mixture models : inference and applications to clustering , 1989 .

[11]  Gary J. Russell,et al.  A Probabilistic Choice Model for Market Segmentation and Elasticity Structure , 1989 .

[12]  H. Bozdogan.  On the information-based measure of covariance complexity and its application to the evaluation of multivariate linear models , 1990 .

[13]  Gary J. Russell,et al.  Measuring Brand Value with Scanner Data , 1993 .

[14]  Pradeep K. Chintagunta,et al.  Investigating Heterogeneity in Brand Preferences in Logit Models for Panel Data , 1991 .

[15]  Adele Cutler,et al.  Information Ratios for Validating Mixture Analysis , 1992 .

[16]  Michel Wedel,et al.  Latent class metric conjoint analysis , 1992 .

[17]  Pradeep K. Chintagunta,et al.  On Using Demographic Variables to Determine Segment Membership in Logit Mixture Models , 1994 .

[18]  W. DeSarbo,et al.  A Review of Recent Developments in Latent Class Regression Models , 1994 .

[19]  Dipak C. Jain,et al.  A Random-Coefficients Logit Brand-Choice Model Applied to Panel Data , 1994 .

[20]  Michel Wedel,et al.  Concomitant Variable Latent Class Models for Conjoint Analysis , 1994 .

[21]  Wagner A. Kamakura,et al.  Issues in the estimation and application of latent structure models of choice , 1994 .

[22]  Hamparsum Bozdogan,et al.  Mixture-Model Cluster Analysis Using Model Selection Criteria and a New Informational Measure of Complexity , 1994 .

[23]  Pradeep K. Chintagunta,et al.  Heterogeneous Logit Model Implications for Brand Positioning , 1994 .

[24]  M. P. Windham,et al.  Information-Based Validity Functionals for Mixture Analysis , 1994 .

[25]  R. Rust,et al.  Model selection criteria: an investigation of relative accuracy, posterior probabilities, and combinations of criteria , 1995 .

[26]  Pradeep K. Chintagunta,et al.  A Framework for Investigating Habits, “The Hand of the Past,” and Heterogeneity in Dynamic Brand Choice , 1996 .

[27]  W. Kamakura,et al.  Modeling Preference and Structural Heterogeneity in Consumer Choice , 1996 .

[28]  G. Celeux,et al.  An entropy criterion for assessing the number of clusters in a mixture model , 1996 .

[29]  Peter S. Fader,et al.  Modeling Consumer Choice among SKUs , 1996 .

[30]  Michel Wedel,et al.  An Exponential-Family Multidimensional Scaling Mixture Methodology , 1996 .

[31]  M. Wedel,et al.  Metric Conjoint Segmentation Methods: A Monte Carlo Comparison , 1996 .

[32]  Michel Wedel,et al.  Representing heterogeneity in consumer response models , 1997 .

[33]  Pradeep K. Chintagunta,et al.  Representing Heterogeneity in Consumer Response Models 1996 Choice Conference Participants , 1997 .

[34]  M. Wedel,et al.  Market Segmentation: Conceptual and Methodological Foundations , 1997 .

[35]  Imran S. Currim,et al.  Models of health plan choice , 1998, Eur. J. Oper. Res..

[36]  Ajay K. Manrai,et al.  Mds Maps for Product Attributes and Market Response: An Application to Scanner Panel Data , 1999 .

[37]  Rick L. Andrews,et al.  Parameter Bias from Unobserved Effects in the Multinomial Logit Model of Consumer Choice , 2000 .

[38]  Rick L. Andrews,et al.  An Empirical Comparison of Logit Choice Models with Discrete versus Continuous Representations of Heterogeneity , 2002 .

[39]  Rick L. Andrews,et al.  Hierarchical Bayes versus Finite Mixture Conjoint Analysis Models: A Comparison of Fit, Prediction, and Partworth Recovery , 2002 .

[40]  Rick L. Andrews,et al.  Identifying segments with identical choice behaviors across product categories: An Intercategory Logit Mixture model , 2002 .