A Latent Class Multidimensional Scaling Model for Two-Way One-Mode Continuous Rating Dissimilarity Data

In this paper, we propose a cluster-MDS model for two-way one-mode continuous rating dissimilarity data. The model aims at partitioning the objects into classes and simultaneously representing the cluster centers in a low-dimensional space. Under the normal distribution assumption, a latent class model is developed in terms of the set of dissimilarities in a maximum likelihood framework. In each iteration, the probability that a dissimilarity belongs to each of the blocks conforming to a partition of the original dissimilarity matrix, and the rest of parameters, are estimated in a simulated annealing based algorithm. A model selection strategy is used to test the number of latent classes and the dimensionality of the problem. Both simulated and classical dissimilarity data are analyzed to illustrate the model.

[1]  James O. Ramsay,et al.  The effect of number of categories in rating scales on precision of estimation of scale values , 1973 .

[2]  Ryszard S. Michalski,et al.  Categories and Concepts: Theoretical Views and Inductive Data Analysis , 1993 .

[3]  Geert De Soete,et al.  A Latent Class Approach to Modeling Pairwise Preferential Choice Data , 1990 .

[4]  Suzanne Winsberg,et al.  A thurstonian pairwise choice model with univariate and multivariate spline transformations , 1993 .

[5]  Susan A. Murphy,et al.  Monographs on statistics and applied probability , 1990 .

[6]  Willem J. Heiser,et al.  A Permutation-Translation Simulated Annealing Algorithm for L1 and L2 Unidimensional Scaling , 2005, J. Classif..

[7]  Michael J. Brusco.  A Simulated Annealing Heuristic for Unidimensional and Multidimensional (City-Block) Scaling of Symmetric Proximity Matrices , 2001, J. Classif..

[8]  Willem J. Heiser,et al.  Global Optimization in Any Minkowski Metric: A Permutation-Translation Simulated Annealing Algorithm for Multidimensional Scaling , 2007, J. Classif..

[9]  Hans-Hermann Bock,et al.  On the Interface between Cluster Analysis, Principal Component Analysis, and Multidimensional Scaling , 1987 .

[10]  Suzanne Winsberg,et al.  A latent class approach to fitting the weighted Euclidean model, clascal , 1993 .

[11]  A. Formann.  Constrained latent class models: Some further applications† , 1989 .

[12]  N. Metropolis,et al.  Equation of State Calculations by Fast Computing Machines , 1953, Resonance.

[13]  A Gordon,et al.  Classification, 2nd Edition , 1999 .

[14]  J. Ramsay.  Maximum likelihood estimation in multidimensional scaling , 1977 .

[15]  Wayne S. DeSarbo,et al.  A latent class probit model for analyzing pick any/N data , 1991 .

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

[17]  J. Vera,et al.  Non-stationary spatial covariance structure estimation in oversampled domains by cluster differences scaling with spatial constraints , 2008 .

[18]  W. DeSarbo,et al.  An exponential family mixture MDS methodology for simultaneous segmentation and product positioning , 1996 .

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

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

[21]  Ru-Qin Yu,et al.  Cluster Analysis by Simulated Annealing , 1994, Comput. Chem..

[22]  Martin Schader,et al.  Knowledge, Data and Computer-Assisted Decisions , 1990, NATO ASI Series.

[23]  Gerhard Winkler,et al.  Image analysis, random fields and dynamic Monte Carlo methods: a mathematical introduction , 1995, Applications of mathematics.

[24]  Mixture decomposition via the simulated annealing algorithm , 1991 .

[25]  P. Groenen,et al.  Cluster differences scaling with a within-clusters loss component and a fuzzy successive approximation strategy to avoid local minima , 1997 .

[26]  J. Ramsay.  Some Statistical Approaches to Multidimensional Scaling Data , 1982 .

[27]  Karl Mosler,et al.  A Cautionary Note on Likelihood Ratio Tests in Mixture Models , 2000 .

[28]  Richard C. Dubes,et al.  Experiments in projection and clustering by simulated annealing , 1989, Pattern Recognit..

[29]  Wayne S. DeSarbo,et al.  Latent Class Multidimensional Scaling. A Review of Recent Developments in the Marketing and Psychometric Literature , 1994 .

[30]  Suzanne Winsberg,et al.  A latent class vector model for preference ratings , 1993 .

[31]  Michael P. Windham,et al.  Information and classification: Concepts, methods and applications , 1995 .

[32]  W. Heiser,et al.  A latent class unfolding model for analyzing single stimulus preference ratings , 1993 .

[33]  M. Lee.  Determining the Dimensionality of Multidimensional Scaling Representations for Cognitive Modeling. , 2001, Journal of mathematical psychology.

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

[35]  Joseph S. Verducci,et al.  Multivariate Statistical Modeling and Data Analysis. , 1988 .

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

[37]  C. D. Gelatt,et al.  Optimization by Simulated Annealing , 1983, Science.

[38]  M. Brusco,et al.  ConPar: a method for identifying groups of concordant subject proximity matrices for subsequent multidimensional scaling analyses , 2005 .

[39]  Willem J. Heiser,et al.  Clustering in Low-Dimensional Space , 1993 .

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

[41]  V. Cerný.  Thermodynamical approach to the traveling salesman problem: An efficient simulation algorithm , 1985 .

[42]  W. DeSarbo,et al.  Multiclus: A new method for simultaneously performing multidimensional scaling and cluster analysis , 1991 .

[43]  Shokri Z. Selim,et al.  A simulated annealing algorithm for the clustering problem , 1991, Pattern Recognit..

[44]  S. Ingrassia.  A comparison between the simulated annealing and the EM algorithms in normal mixture decompositions , 1992 .

[45]  Robert R. Sokal,et al.  A statistical method for evaluating systematic relationships , 1958 .

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

[47]  U. Böckenholt,et al.  Modeling Individual Differences in Unfolding Preference Data: A Restricted Latent Class Approach , 1990 .

[48]  G. McLachlan,et al.  The EM algorithm and extensions , 1996 .

[49]  Ulf Böckenholt,et al.  Constrained latent class analysis: Simultaneous classification and scaling of discrete choice data , 1991 .

[50]  Using latent class analysis in categorization research , 1993 .

[51]  R. Bagozzi.  Advanced Methods of Marketing Research , 1994 .

[52]  A. Raftery,et al.  Model-Based Clustering With Dissimilarities: A Bayesian Approach , 2007 .

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

[54]  J. Ware,et al.  Applications of Statistics , 1978 .