Kamel Jedidi

Clustering at the Movies

Weekly box office revenues for approximately 100 successful motion pictures are analyzed by use of a finite mixture regression technique to determine if regular sales patterns emerge. Based on an exponential decay model applied to market share data, four clusters of movies, varying in opening strength and decay rate, are found. Characteristics of the clusters and implications for future research are discussed.

Bayesian factor analysis for multilevel binary observations

Multilevel covariance structure models have become increasingly popular in the psychometric literature in the past few years to account for population heterogeneity and complex study designs. We develop practical simulation based procedures for Bayesian inference of multilevel binary factor analysis models. We illustrate how Markov Chain Monte Carlo procedures such as Gibbs sampling and Metropolis-Hastings methods can be used to perform Bayesian inference, model checking and model comparison without the need for multidimensional numerical integration. We illustrate the proposed estimation methods using three simulation studies and an application involving students achievement results in different areas of mathematics.

Multiclus: A new method for simultaneously performing multidimensional scaling and cluster analysis

This paper develops a maximum likelihood based method for simultaneously performing multidimensional scaling and cluster analysis on two-way dominance or profile data. This MULTICLUS procedure utilizes mixtures of multivariate conditional normal distributions to estimate a joint space of stimulus coordinates andK vectors, one for each cluster or group, in aT-dimensional space. The conditional mixture, maximum likelihood method is introduced together with an E-M algorithm for parameter estimation. A Monte Carlo analysis is presented to investigate the performance of the algorithm as a number of data, parameter, and error factors are experimentally manipulated. Finally, a consumer psychology application is discussed involving consumer expertise/experience with microcomputers.

Heterogeneous factor analysis models: A bayesian approach

Multilevel factor analysis models are widely used in the social sciences to account for heterogeneity in mean structures. In this paper we extend previous work on multilevel models to account for general forms of heterogeneity in confirmatory factor analysis models. We specify various models of mean and covariance heterogeneity in confirmatory factor analysis and develop Markov Chain Monte Carlo (MCMC) procedures to perform Bayesian inference, model checking, and model comparison.We test our methodology using synthetic data and data from a consumption emotion study. The results from synthetic data show that our Bayesian model perform well in recovering the true parameters and selecting the appropriate model. More importantly, the results clearly illustrate the consequences of ignoring heterogeneity. Specifically, we find that ignoring heterogeneity can lead to sign reversals of the factor covariances, inflation of factor variances and underappreciation of uncertainty in parameter estimates. The results from the emotion study show that subjects vary both in means and covariances. Thus traditional psychometric methods cannot fully capture the heterogeneity in our data.

Identifying Sources of Heterogeneity for Empirically Deriving Strategic Types: A Constrained Finite-Mixture Structural-Equation Methodology

The resource-based view (RBV) of the firm suggests that strategic deployment of capabilities allows strategic business units (SBUs) to exploit distinctive competencies and create sustainable competitive advantage. Following the RBV, we propose a new predictive methodology for deriving typologies of SBUs that accommodates heterogeneity among SBUs with respect to their strategic capabilities, how effectively they are employed, and performance. Statistically, we devise a constrained finite-mixture structural-equation procedure that simultaneously accounts for firm capabilities, performance outcomes, and the relationships between them. The procedure allows for a comprehensive modeling and grouping of entities, and simultaneously provides a diagnosis of the sources of heterogeneity via the flexibility of estimating a series of nested models. Managerially, our proposed methodology is grounded in the strategic type and RBV literature and can capture the effects of environmental and industry-specific factors. Using data obtained from 216 SBUs in the United States for illustration, the results show that our derived four mixed-type solution dominates the four-group, Prospectors-Analyzers-Defenders-Reactors classification as well as a number of other nested model solutions in terms of objective statistical fit criteria for this data set, suggesting a more contingency-driven strategic stance adopted by these SBUs. We conclude with a discussion of the theoretical and managerial benefits of an improved methodology for empirically deriving strategic typologies.

Probabilistic Subset-Conjunctive Models for Heterogeneous Consumers

The authors propose two generalizations of conjunctive and disjunctive screening rules. First, they relax the requirement that an acceptable alternative must be satisfactory on one criterion (disjunctive) or on all criteria (conjunctive). Second, they relax the assumption that consumers make deterministic judgments when evaluating alternatives. They combine the two generalizations into a probabilistic subset-conjunctive rule, which allows consumers to use any number or subset of decision criteria when screening alternatives and permits them to be uncertain about the acceptability of attribute levels. These two features allow for a screening process that is uncertain and more flexible than the deterministic conjunctive and disjunctive rules currently described in the literature. The authors describe a latent-class method for the estimation of the subset-conjunctive rules and the attribute-level consideration probabilities using either consideration or choice data. Applications using both types of data suggest that the proposed models predict as well as linear models do; can make different predictions of consideration, choice, and market shares; and provide insights into consumer decision processes that are different from those obtained with linear models.

Simultaneous Multidimensional Unfolding and Cluster Analysis: An Investigation of Strategic Groups

This paper develops a maximum likelihood based methodology for simultaneously performing multidimensional unfolding and cluster analysis on two-way dominance or profile data. This new procedure utilizes mixtures of multivariate conditional normal distributions to estimate a joint space of stimulus coordinates and K ideal points, one for each cluster or group, in a T-dimensional space. The conditional mixture, maximum likelihood methodology is introduced together with an E-M algorithm utilized for parameter estimation. A marketing strategy application is provided with an analysis of PIMS data for a set of firms drawn from the same competitive industry to determine strategic groups, while simultaneously depicting strategy-performance relationships.

A maximum likelihood method for latent class regression involving a censored dependent variable

The standard tobit or censored regression model is typically utilized for regression analysis when the dependent variable is censored. This model is generalized by developing a conditional mixture, maximum likelihood method for latent class censored regression. The proposed method simultaneously estimates separate regression functions and subject membership in K latent classes or groups given a censored dependent variable for a cross-section of subjects. Maximum likelihood estimates are obtained using an EM algorithm. The proposed method is illustrated via a consumer psychology application.

Willingness to Pay: Measurement and Managerial Implications

Accurately measuring consumers’ willingness to pay (WTP) is central to any pricing decision. This chapter attempts to synthesize the theoretical and empirical literatures on WTP. We fi rst present the various conceptual defi nitions of WTP. Then, we evaluate the advantages and disadvantages of alternative methods that have been proposed for measuring it. In this analysis, we distinguish between methods based on purchase data and those based on survey/experimental data (e.g. self-stated WTP, contingent valuation, conjoint analysis and experimental auctions). Finally, using numerical examples, we illustrate how managers can use WTP measures to make key strategic decisions involving bundling, nonlinear pricing and product line pricing.

Representing Heterogeneity in Consumer Response Models 1996 Choice Conference Participants

We define sources of heterogeneity in consumer utility functions relatedto individual differences in response tendencies, drivers of utility, formof the consumer utility function, perceptions of attributes, statedependencies, and stochasticity. A variety of alternative modelingapproaches are reviewed that accommodate subsets of these various sourcesincluding clusterwise regression, latent structure models, compounddistributions, random coefficients models, etc. We conclude by defining anumber of promising research areas in this field.