Abstract
The p-median offers an alternative to centroid-based clustering algorithms for identifying unobserved categories. However, existing p-median formulations typically require data aggregation into a single proximity matrix, resulting in masked respondent heterogeneity. A proposed three-way formulation of the p-median problem explicitly considers heterogeneity by identifying groups of individual respondents that perceive similar category structures. Three proposed heuristics for the heterogeneous p-median (HPM) are developed and then illustrated in a consumer psychology context using a sample of undergraduate students who performed a sorting task of major U.S. retailers, as well as a through Monte Carlo analysis.
Similar content being viewed by others
Notes
The choices of both the measure of similarity between proximity matrices (Step 1) and the clustering method to use (Step 2) are arbitrary. Neither step relates directly to the objective function Z (i.e., they optimize two different objectives), so we use the Frobenius norm and complete linkage, which provide a quick solution for heuristic C and provide input to the C+IH heuristic.
Let l jg be the index indicating the median associated with object j for an individual member of group g. Then, \(\hat{d}_{ijk}=\sum _{j=1}^{J-1}\sum _{k=j+1}^{J}\sum _{g=1}^{G}p_{ig}d_{i(l_{jg})(l_{kg})}\).
The median stores appear in italics.
References
Addelman, S. (1962). Orthogonal main-effect plans for asymmetrical factorial experiments. Technometrics, 4(1), 21–46.
Ashby, F.G., Maddox, T.W., & Lee, W.W. (1994). On the dangers of average across subjects when using multidimensional scaling or the similarity-choice model. Psychological Science, 5(3), 144–151.
Baum, E.B. (1986). Toward practical ‘neural’ computation for combinatorial optimization problems. In J. Denker (Ed.), Neural networks for computing (pp. 53–64). New York: American Institute of Physics.
Berman, O., & Drezner, Z. (2008). The p-median problem under uncertainty. European Journal of Operations Research, 189(1), 19–30.
Bettman, J.R., Luce, M.F., & Payne, J.W. (1998). Constructive consumer choice processes. Journal of Consumer Research, 25(3), 187–217.
Bijmolt, T.H.A., & Wedel, M. (1995). The effects of alternative methods of collecting similarity data for multidimensional scaling. International Journal of Research in Marketing, 12(4), 363–371.
Blanchard, S.J., DeSarbo, W.S., Atalay, A.S., & Harmancioglu, N. (2012). Identifying consumer heterogeneity in unobserved categories. Marketing Letters, 23(1), 177–194.
Boone, L.E., & Kurtz, D.L. (2009). Contemporary marketing. Mason: South-Western Educational Publishing.
Brusco, M.J., Cradit, J.D., & Tashchian, A. (2003). Multicriterion clusterwise regression for joint segmentation settings: an application to customer value. Journal of Marketing Research, 40(2), 225–234.
Brusco, M.J., & Cradit, J.D. (2005). ConPar: a method for identifying groups of concordant subject proximity matrices for subsequent multidimensional scaling analyses. Journal of Mathematical Psychology, 49(2), 142–154.
Brusco, M.J., & Köhn, H.-F. (2008a). Comment on ‘Clustering by passing messages between data points’. Science, 319(5864), 726.
Brusco, M.J., & Köhn, H.-F. (2008b). Optimal partitioning of a data set based on the p-median problem. Psychometrika, 73(1), 89–105.
Brusco, M.J., & Köhn, H.-F. (2009). Exemplar-based clustering via simulated annealing. Psychometrika, 74(3), 457–475.
Conn, A.R., Scheinberg, K., & Vincente, L.N. (2009). Introduction to derivative-free optimization. Philadelphia: SIAM.
Coxon, A.P.M. (1999). Sorting data: collection and analysis. Thousand Oaks: Sage.
Crainic, T.G., Gendreau, M., Hansen, P., & Mladenović, N. (2007). Cooperative parallel variable neighborhood search for the p-median. Journal of Heuristics, 10(3), 293–314.
Daws, J.T. (1996). The analysis of free-sorting data: beyond pairwise co-occurrence. Journal of Classification, 13(1), 57–80.
DeSarbo, W.S. (1982). GENNCLUS: new models for general nonhierarchical clustering analysis. Psychometrika, 47(4), 436–449.
DeSarbo, W.S., & Carroll, J.D. (1985). Three-way metric unfolding via alternating weighted least squares. Psychometrika, 50(3), 275–300.
DeSarbo, W.S., & Cron, W.L. (1988). A maximum likelihood methodology clusterwise linear regression. Journal of Classification, 5(2), 249–289.
Farquhar, P.H., Han, J.Y., Herr, P.M., & Ijiri, Y. (1992). Strategies for leveraging master-brands. Marketing Research, 4(3), 32–43.
Fazio, R.H., & Dunton, B.C. (1997). Categorization by race: the impact of automatic and controlled components of racial prejudice. Journal of Experimental Social Psychology, 33(5), 451–470.
Forgy, E.W. (1965). Cluster analysis of multivariate data: efficiency vs. interpretability of classifications. Biometrics, 21(3), 768–769.
Floudas, C.A. (1995). Non-linear and mixed-integer optimisation. New York: Oxford University Press.
Furnas, G.W. (1989). Metric family portraits. Journal of Classification, 6(1), 7–52.
Gigerenzer, G., & Todd, P.M. (1999). Simple heuristics that make us smart. New York: Oxford University Press.
Griffin, A., & Hauser, J.R. (1993). The voice of the customer. Marketing Science, 12(1), 1–27.
Hansen, P., Brimberg, J., Urosevic, D., & Mladenović, N. (2009). Solving large p-median clustering problems by primal-dual variable neighborhood search. Data Mining and Knowledge Discovery, 19(3), 351–375.
Hansen, P., & Mladenović, N. (2001). Variable neighborhood search: principles and applications. European Journal of Operational Research, 130, 449–467.
Hauser, J.R., Toubia, O., Evgeniou, T., Befurt, R., & Dzyabura, D. (2010). Disjunctions of conjunctions, cognitive simplicity, and consideration sets. Journal of Marketing Research, 47(3), 485–496.
Helsen, K., & Green, P. (1991). A computational study of replicated clustering with an application to market segmentation. Decision Sciences, 22(5), 1124–1141.
Hubert, L., & Arabie, P. (1985). Comparing partitions. Journal of Classification, 2(1), 193–218.
Isen, A.M. (1984). Toward understanding the role of affect in cognition. In R.S. Wyer Jr. & T.K. Srull (Eds.), Handbook of social cognition (pp. 179–236). Hillsdale: Lawrence Erlbaum.
Ilog (2006). ILOG CPLEX 10.0 user’s manual.
Jedidi, K., & DeSarbo, W.S. (1991). A stochastics multidimensional scaling methodology for the spatial representation of three-mode, three-way pick any/J data. Psychometrika, 56(3), 471–494.
John, D.R., & Sujan, M. (1990). Age differences in product categorization. Journal of Consumer Research, 16(March), 452–460.
Johnson, S.C. (1967). Hierarchical clustering schemes. Psychometrika, 32(3), 241–254.
Kalamas, M., Cleveland, M., Laroche, M., & Laufer, R. (2006). The critical role of congruency in prototypical brand extensions. Journal of Strategic Marketing, 14(3), 193–210.
Kariv, O., & Hakimi, S.L. (1979). An algorithmic approach to network location problems. II: the p-medians. SIAM Journal on Applied Mathematics, 37(3), 539–560.
Kaufman, L., & Rousseeuw, P.J. (2005). Finding groups in data: an introduction to cluster analysis. New York: Wiley.
Kelter, S., Cohen, R., Engel, D., List, G., & Stronher, H. (1977). The conceptual structure of aphasic and schizophrenic patients in a nonverbal sorting task. Journal of Psycholinguistic Research, 6(4), 279–303.
Klastorin, T. (1985). The p-median problem for cluster analysis: a comparative test using the mixture model approach. Management Science, 31(1), 84–95.
Köhn, H.-F., Steinley, D., & Brusco, M.J. (2010). The p-median as a tool for clustering psychological data. Psychological Methods, 15(1), 87–95.
Lakey, B., & Cassady, P.B. (1990). Cognitive processes in perceived social support. Personality Processes and Individual Differences, 59(2), 337–343.
Langley, P. (1996). Elements of machine learning. San Francisco: Morgan Kaufmann.
Lee, M.D. (2001). Determining the dimensionality of mutli-dimensional scaling represetations for cognitive modeling. Journal of Mathematical Psychology, 45(1), 149–166.
Love, B.C. (2003). Concept learning. In L. Nadel (Ed.), The encyclopedia of cognitive science (pp. 646–652). London: Nature Publishing Group.
Maranzana, F.E. (1963). On the location of supply points to minimize transportation costs. IBM Systems Journal, 2(2), 129–135.
Medin, D.L., & Schaffer, M.M. (1978). Context theory of classification learning. Psychological Review, 85(3), 207–238.
Mervis, C.B., Catlin, J., & Rosch, E. (1976). Relationships among goodness-of-example, category norms, and word frequency. Bulletin of the Psychonomic Society, 7(3), 283–294.
Miller, G.A. (1969). A psychological method to investigate verbal concepts. Journal of Mathematical Psychology, 6(2), 169–191.
Mladenović, N., Brimberg, J., Hansen, P., & Moreno-Perez, J.A. (2007). The p-median problem: a survey of metaheuristic approaches. European Journal of Operational Research, 179(3), 927–939.
Mladenović, N., & Hansen, P. (1997). Variable neighborhood search. Computers & Operations Research, 24(11), 1097–1100.
Perkins, W.S. (1993). The effects of experience and education on the organization of marketing knowledge. Psychology & Marketing, 10(3), 169–183.
Rao, V.R., & Katz, R. (1971). Alternative multidimensional scaling methods for large stimulus sets. Journal of Marketing Research, 8(4), 488–494.
Reed, S.K. (1972). Pattern recognition and categorization. Cognitive Psychology, 3(3), 382–407.
Reed, S.K. (1978). Category vs. item learning: implications for categorization models. Memory & Cognition, 6(6), 612–621.
Rosch, E., & Mervis, C.B. (1975). Family resemblances: studies in the internal structure of categories. Cognitive Psychology, 7(4), 573–605.
Rosch, E., Simpson, C., & Miller, R.S. (1976). Structural bases of typicality effects. Journal of Experimental Psychology. Human Perception and Performance, 2(4), 491–502.
Ross, B.H., & Murphy, G.L. (1999). Food for thought: cross-classification and category organization in a complex real-world domain. Cognitive Psychology, 38(4), 495–554.
Rousseeuw, P.J. (1987). Silhouettes: a graphical aid to the interpretation and validation of cluster analysis. Journal of Computational and Applied Mathematics, 20(November), 53–65.
Shugan, S.M. (1980). The cost of thinking. Journal of Consumer Research, 7(2), 99–111.
Simon, H.A. (1955). A behavioral model of rational choice. Quarterly Journal of Economics, 69(1), 99–118.
Smith, E.R., Fazio, R.H., & Cejka, M.A. (1996). Accessible attitudes influence categorization of multiply categorizable objects. Journal of Personality and Social Psychology, 71(5), 888–898.
Sujan, M., & Dekleva, C. (1987). Product categorization and inference making: some implications for comparative advertising. Journal of Consumer Research, 14(3), 372–378.
Takane, Y. (1980). Analysis of categorizing behavior using a quantification method. Behaviormetrika, 7(8), 75–86.
Tucker, L.R., & Messick, S.J. (1963). An individual differences model for multidimensional scaling. Psychometrika, 28(4), 333–367.
Urban, G.L., Hulland, J.S., & Weinberg, B.D. (1993). Premarket forecasting for new consumer durable goods: modeling categorization, elimination, and consideration phenomena. Journal of Marketing, 57(2), 47–63.
Vapnik, V. (1998). Statistical learning theory. New York: Wiley.
Ward, J.H. (1963). Hierarchical grouping to optimize an objective function. Journal of the American Statistical Association, 38(301), 236–244.
Wedel, M., & Kamakura, W.A. (2000). Market segmentation: conceptual and methodological foundations. Norwell: Kluwer Academic.
Yang, C.C., & Yang, C.C. (2007). Separating latent classes by information criteria. Journal of Classification, 24(2), 183–203.
Acknowledgements
We wish to thank the Editor, the Associate Editor, and three anonymous reviewers for their constructive comments which have helped improve the contribution and quality of this manuscript.
Author information
Authors and Affiliations
Corresponding author
Appendix: Automatic Search Procedure for Penalty Term δ
Appendix: Automatic Search Procedure for Penalty Term δ
Optimizing Z and leaving δ to be estimated always leads to a trivial solution of δ=0. As such, we propose to identify a value of δ by optimizing a somewhat auxiliary objective function h(δ). This function compares the structures obtained by solving the HPM problem Z and the piles provided by each individual participant in the sorting task using the Adjusted Rand Index (Hubert & Arabie, 1985). The shape and space of function h(δ) is not known exactly but assumes known category structures so its derivatives are not available and direct estimation is not possible. However, we attempt to solve the problem of estimating δ by Derivative-Free Optimization (DFO) methods (Conn, Scheinberg, & Vicente, 2009) by using a simplified physics surrogate: a function that approximates the real function. First to evaluate h(δ), for a given δ, we proceed as follows:
-
1.
Solve HPM in (10) using δ, for all g=1,…,G. Use one application of the constructive heuristic and the improvement heuristic (C+IH). Denote C g for g=1,…,G, for the solutions obtained.
-
2.
For all g=1,…,G, compute the Adjusted Rand Index between each individual’s estimated category structure and the piles created. Let \(\mathit{ARI}_{C_{g}}\) be the Adjusted Rand Index obtained using solution C g .
-
3.
Let \(h(\delta)=\mathit{average}(\mathit{ARI}_{C_{g}})\).
1.1 A.1 Optimizing h(δ)
The proposed DFO consists of a univariate pattern-search method that takes a pair of search directions γ and −γ for h(δ) at each iteration. First, it evaluates the function at a unit step length along each direction. The (candidate) solutions obtained form a frame around the current iterate (i.e. current best solution for h(δ)). If either h(δ−γ) or h(δ+γ) is greater than h(δ) (recall the goal of maximizing ARI), it becomes the new best solution, the center of the frame shifts to this new value of δ, and the frame is augmented. If neither h(δ−γ) or h(δ+γ) improve on h(δ), the frame shrinks. Such iterations repeat until a stopping criterion is met (e.g., number of h(δ) evaluations, minimum size of γ, maximum allowed time).
For certain DFO methods, it is possible to prove global convergence to a stationary point of the function being optimized. The presence of noise and other forms of inexactness may affect the performance of the pattern-search algorithm (e.g., use of an inexact solution for C g ) and convergence. Yet it should suffice to provide a good solution for δ that can be used along with the heuristics presented herein. The algorithm in Figure A1 presents the pseudo-code of the proposed pattern-search method for this automated penalty selection.
Rights and permissions
About this article
Cite this article
Blanchard, S.J., Aloise, D. & DeSarbo, W.S. The Heterogeneous P-Median Problem for Categorization Based Clustering. Psychometrika 77, 741–762 (2012). https://doi.org/10.1007/s11336-012-9283-3
Received:
Revised:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11336-012-9283-3