Model Selection in Mixture Regression Analysis-A Monte Carlo Simulation Study

Mixture regression models have increasingly received attention from both marketing theory and practice, but the question of selecting the correct number of segments is still without a satisfactory answer. Various authors have considered this problem, but as most of available studies appeared in statistics literature, they aim to exemplify the effectiveness of new proposed measures, instead of revealing the performance of measures commonly available in statistical packages. The study investigates how well commonly used information criteria perform in mixture regression of normal data, with alternating sample sizes. In order to account for different levels of heterogeneity, this factor was analyzed for different mixture proportions. As existing studies only evaluate the criteria’s relative performance, the resulting success rates were compared with an outside criterion, so called chance models. The findings prove helpful for specific constellations.

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

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

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

[4]  Rick L. Andrews,et al.  A Comparison of Segment Retention Criteria for Finite Mixture Logit Models , 2003 .

[5]  D. Bell,et al.  Looking for Loss Aversion in Scanner Panel Data: The Confounding Effect of Price Response Heterogeneity , 2000 .

[6]  Jie Zhang,et al.  Customizing Promotions in Online Stores , 2004 .

[7]  D. G. Morrison.  On the Interpretation of Discriminant Analysis , 1969 .

[8]  A. Stam,et al.  Optimal Pricing Strategies for an Automotive Aftermarket Retailer , 2006 .

[9]  A. Freeman.  A Fuzzy Set Model of Search and Consideration with an Application to an Online Market , 2003 .

[10]  A. Koehler,et al.  A Comparison of the Akaike and Schwarz Criteria for Selecting Model Order , 1988 .

[11]  D. Rubin,et al.  Testing the number of components in a normal mixture , 2001 .

[12]  P. Danaher,et al.  A Comparison of Online and Offline Consumer Brand Loyalty , 2003 .

[13]  P. Danaher.  Optimal Pricing of New Subscription Services: Analysis of a Market Experiment , 2002 .

[14]  H. Bozdogan,et al.  Multi-sample cluster analysis using Akaike's Information Criterion , 1984 .

[15]  Frenkel Ter,et al.  Identifying Spatial Segments in International Markets , 2002 .

[16]  A. Rangaswamy,et al.  A Fuzzy Set Model of Search and Consideration with an Application to an Online Market , 2003 .

[17]  D. Sjoquist,et al.  Estimating Differential Responses to Local Fiscal Conditions: A Mixture Model Analysis , 2005 .

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

[19]  B. Everitt.  A Monte Carlo Investigation Of The Likelihood Ratio Test For The Number Of Components In A Mixture Of Normal Distributions. , 1981, Multivariate behavioral research.

[20]  F. Leisch,et al.  Fitting Finite Mixtures of Linear Regression Models with Varying & Fixed Eects in R , 2006 .

[21]  Teck-Hua Ho,et al.  A Parsimonious Model of Stockkeeping-Unit Choice , 2003 .

[22]  M. Agarwal.  Developing Global Segments and Forecasting Market Shares: A Simultaneous Approach Using Survey Data , 2003 .

[23]  Carrie M. Heilman,et al.  Determinants of Product-Use Compliance Behavior , 2004 .

[24]  Michael Lewis.  Incorporating Strategic Consumer Behavior into Customer Valuation , 2005 .

[25]  S. Yoo.  Application of a mixture model to approximate bottled water consumption distribution , 2003 .

[26]  D. Rubin,et al.  Estimation and Hypothesis Testing in Finite Mixture Models , 1985 .

[27]  D. M. Allen,et al.  Determining the number of components in mixtures of linear models , 2001 .

[28]  Frank Huber,et al.  Capturing Customer Heterogeneity using a Finite Mixture PLS Approach , 2002 .

[29]  Ursula Y. Sullivan,et al.  Managing Marketing Communications with Multichannel Customers , 2005 .

[30]  R. Kohli,et al.  Probabilistic Subset-Conjunctive Models for Heterogeneous Consumers , 2005 .

[31]  Carlos C. Rodri guez.  The ABC of Model Selection: AIC, BIC and the New CIC , 2005 .

[32]  R. Rust,et al.  Optimizing the Marketing Interventions Mix in Intermediate-Term CRM , 2005 .

[33]  Friedrich Leisch,et al.  Fitting finite mixtures of generalized linear regressions in R , 2007, Comput. Stat. Data Anal..

[34]  Ana Oliveira-Brochado,et al.  Examining the Segment Retention Problem for the Group Satellite Case , 2006 .

[35]  J. Vermunt,et al.  Latent Gold 4.0 User's Guide , 2005 .

[36]  Neal O. Jeffries.  A note on 'Testing the number of components in a normal mixture' , 2003 .

[37]  Sunil Gupta,et al.  Brand Choice, Purchase Incidence, and Segmentation: An Integrated Modeling Approach , 1992 .

[38]  D.,et al.  Regression Models and Life-Tables , 2022 .

[39]  Bharat Anand,et al.  Brands as Beacons: A New Source of Loyalty to Multiproduct Firms , 2004 .

[40]  Geoffrey J. McLachlan,et al.  Finite Mixture Models , 2019, Annual Review of Statistics and Its Application.

[41]  R. Srinivasan.  Dual Distribution and Intangible Firm Value: Franchising in Restaurant Chains , 2006 .

[42]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[43]  A. F. Smith,et al.  Statistical analysis of finite mixture distributions , 1986 .

[44]  Rick L. Andrews,et al.  Retention of latent segments in regression-based marketing models , 2003 .

[45]  R. Srinivasan,et al.  Dual Distribution and Intangible Firm Value: Franchising in Restaurant Chains , 2006 .

[46]  W. Reinartz,et al.  Balancing Acquisition and Retention Resources to Maximize Customer Profitability , 2005 .

[47]  L. Wasserman,et al.  Exploring Some Analytical Characteristics of Finite Mixture Models , 2006 .

[48]  Michael Lewis.  The Influence of Loyalty Programs and Short-Term Promotions on Customer Retention , 2004 .

[49]  B. Leroux.  Consistent estimation of a mixing distribution , 1992 .

[50]  Marko Sarstedt,et al.  Sample- and segment-size specific Model Selection in Mixture Regression Analysis , 2006 .

[51]  Ana Oliveira-Brochado,et al.  Assessing the Number of Components in Mixture Models: a Review , 2005 .

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

[53]  J. Rissanen,et al.  Modeling By Shortest Data Description* , 1978, Autom..

[54]  R. Shachar,et al.  Cast Demographics, Unobserved Segments, and Heterogeneous Switching Costs in a Television Viewing Choice Model , 2000 .

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

[56]  Ran Kivetz,et al.  The Goal-Gradient Hypothesis Resurrected: Purchase Acceleration, Illusionary Goal Progress, and Customer Retention , 2006 .

[57]  Michel Wedel,et al.  Bayesian Prediction in Hybrid Conjoint Analysis , 2002 .

[58]  V. Rao,et al.  A General Choice Model for Bundles with Multiple-Category Products: Application to Market Segmentation and Optimal Pricing for Bundles , 2003 .

[59]  W. DeSarbo,et al.  Customer Value Analysis in a Heterogeneous Market , 2001 .

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

[61]  Pradeep K. Chintagunta,et al.  The Augmented Latent Class Model: Incorporating Additional Heterogeneity in the Latent Class Model for Panel Data , 2004 .

[62]  W. DeSarbo,et al.  Market Segment Derivation and Profiling Via a Finite Mixture Model Framework , 2002 .

[63]  B. Everitt.  A Monte Carlo Investigation of the Likelihood Ratio Test for Number of Classes in Latent Class Analysis. , 1988, Multivariate behavioral research.

[64]  Gérard Govaert,et al.  Assessing a Mixture Model for Clustering with the Integrated Completed Likelihood , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[65]  Carrie M. Heilman,et al.  The Evolution of Brand Preferences and Choice Behaviors of Consumers New to a Market , 2000 .

[66]  F. Leisch.  FlexMix: A general framework for finite mixture models and latent class regression in R , 2004 .

[67]  Tōkei Sūri Kenkyūjo.  Annals of the Institute of Statistical Mathematics , 1949 .

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

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

[70]  W. DeSarbo,et al.  Finite-Mixture Structural Equation Models for Response-Based Segmentation and Unobserved Heterogeneity , 1997 .

[71]  B. Muthén,et al.  Deciding on the Number of Classes in Latent Class Analysis and Growth Mixture Modeling: A Monte Carlo Simulation Study , 2007 .

[72]  S. Sclove.  Application of model-selection criteria to some problems in multivariate analysis , 1987 .

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

[74]  Peter J. Danaher,et al.  Optimizing Television Program Schedules Using Choice Modeling , 2001 .

[75]  Jacquelyn S. Thomas.  A Methodology for Linking Customer Acquisition to Customer Retention , 2001 .

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

[77]  W. DeSarbo,et al.  The Spatial Representation of Market Information , 2001 .

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