Journal of Classification

, Volume 12, Issue 2, pp 243–263 | Cite as

Additive two-mode clustering: The error-variance approach revisited

  • Boris Mirkin
  • Phipps Arabie
  • Lawrence J. Hubert


The additive clustering approach is applied to the problem of two-mode clustering and compared with the recent error-variance approach of Eckes and Orlik (1993). Although the schemes of the computational algorithms look very similar in both of the approaches, the additive clustering has been shown to have several advantages. Specifically, two technical limitations of the error-variance approach (see Eckes and Orlik 1993, p. 71) have been overcome in the framework of the additive clustering.


Two-mode clustering Additive clustering Correspondence analysis Addition/delection algorithm 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. ARABIE, P., and HUBERT, L. (1992), “Combinatorial Data Analysis,”Annual Review of Psychology, 43, 169–203.CrossRefGoogle Scholar
  2. ARABIE, P., SCHLEUTERMANN, S., DAWS, J., and HUBERT, L. J. (1988), “Marketing Applications of Sequencing and Partitioning of Nonsymmetric and/or Two-mode Matrices”, inData, Expert Knowledge and Decision, Eds., W. Gaul, and M. Schader, Berlin: Springer-Verlag, 215–224.Google Scholar
  3. BASS, F. M., PESSEMIER, E. A., and LEHMANN, D. R. (1972), “An Experimental Study of Relationships between Attitudes, Brand Preference, and Choice,”Behavioral Science, 17, 532–541.CrossRefGoogle Scholar
  4. BRAVERMAN, E.M., KISELEVA, N.E., MUCHNIK, I.B., and NOVIKOV, S.G. (1974), “Linguistic Approach to the Problem of Processing Large Bodies of Data”,Automation and Remote Control, 35, (11, part 1), 1768–1788.MATHGoogle Scholar
  5. CARLIER, A., and KROONENBERG, P. M. (1993), “Biplots and Decompositions in Twoway and Three-way Correspondence Analysis,” inPublications du Laboratoire de Statistique et Probabilités, Université Paul Sabatier, Toulouse (France), 01-93, 1–31.Google Scholar
  6. COLOMBO, R. A., and MORRISON, D. G. (1989), “A Brand Switching Model with Implications for Marketing Strategies”,Marketing Science, 8, 89–99.CrossRefGoogle Scholar
  7. DESARBO, W. S. (1982), ‘GENNCLUS: New Models for General Nonhierarchical Clustering Analysis,”Psychometrika, 47, 446–449.MathSciNetGoogle Scholar
  8. DESARBO, W. S., and DE SOETE, G. (1984), “On the Use of Hierarchical Clustering for the Analysis of Nonsymmetric Proximities,”Journal of Consumer Research, 11, 601–610.CrossRefGoogle Scholar
  9. ECKES, T., (1993), “A Two-mode Clustering Study of Situations and Their Features”, inInformation and Classification, Eds., O. Opitz, B. Lausen, and R. Klar, New York: Springer-Verlag, 510–517.Google Scholar
  10. ECKES, T., and ORLIK, P. (1991), “An Agglomerative Method for Two-mode Hierarchical Clustering,” inClassification, Data Analysis, and Knowledge Organization, Eds., H.-H. Bock and P. Ihm, Berlin: Springer-Verlag, 3–8.Google Scholar
  11. ECKES, T., and ORLIK, P. (1993), “An Error Variance Approach to Two-mode Hierarchical Clustering,”Journal of Classification, 10, 51–74.MATHCrossRefGoogle Scholar
  12. GREENACRE, M. J. (1984),Theory and Applications of Correspondence Analysis, London: Academic Press.MATHGoogle Scholar
  13. GREENACRE, M., and BLASIUS, J. (Eds.) (1994),Correspondence Analysis: Recent Developments and Applications, New York: Academic Press.Google Scholar
  14. HARTIGAN, J.A. (1972), “Direct Clustering of a Data Matrix”,Journal of American Statistical Association, 67, 123–129.CrossRefGoogle Scholar
  15. HARTIGAN, J. A. (1976), “Modal Blocks in Dentition of West Coast Mammals”,Systematic Zoology, 25, 149–160.CrossRefGoogle Scholar
  16. LEBART, L., and MIRKIN, B. (1993), “Correspondence Analysis and Classification”, inMultivariate Analysis: Future Directions 2., Amsterdam: Elsevier, 341–357.Google Scholar
  17. LEBART, L., MORINEAU, A., and WARWICK, K. M. (1984),Multivariate Descriptive Statistical Analysis: Correspondence Analysis and Related Techniques for Large Matrices (E. M. Berry, Trans.), New York: Wiley. (Original work published 1977).MATHGoogle Scholar
  18. MIRKIN, B. (1987), “Additive Clustering and Qualitative Factor Analysis Methods for Similarity Matrices,”Journal of Classification, 4, 7–31; (1989) Erratum,6, 271–272.MATHCrossRefMathSciNetGoogle Scholar
  19. MIRKIN, B., “Clustering for Contingency Tables: Boxes and Partitions”,Statistics and Computing, in press.Google Scholar
  20. MIRKIN, B., and ROSTOVTSEV, P. S. (1978), “Method to Reveal Associated Subsets of the Variables”, inModels for Socioeconomic Data Aggregation, Ed., B. Mirkin, Novosibirsk, Institute of Economics Press, 107–112.Google Scholar
  21. NISHISATO, S. (1980),Analysis of Categorical Data: Dual Scaling and Its Applications, Toronto: University of Toronto Press.MATHGoogle Scholar
  22. NISHISATO, S. (1994),Elements of Dual Scaling, Hillsdale, NJ: Erlbaum.Google Scholar
  23. PACKER, C.V. (1989), “Applying Row-Column Permutation to Matrix Representations of Large Citation Networks”,Information Processing & Management, 25, 307–314.CrossRefGoogle Scholar
  24. PRICE, R. H. (1974), “The Taxonomic Classification of Behaviors and Situations and the Problem of Behavior-Environment Congruence,”Human Relations, 27, 567–585.CrossRefGoogle Scholar
  25. PRICE, R. H., and BOUFFARD, D. L. (1974), “Behavioral Appropriateness and Situational Constraint as Dimensions of Social Behavior,”Journal of Personality and Social Psychology, 30, 579–586.CrossRefGoogle Scholar
  26. SHEPARD, R. N., and ARABIE, P. (1979), “Additive Clustering: Representation of Similarities as Combinations of Discrete Overlapping Properties,”Psychological Review, 86, 87–123.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag 1995

Authors and Affiliations

  • Boris Mirkin
    • 1
    • 2
  • Phipps Arabie
    • 3
  • Lawrence J. Hubert
    • 4
  1. 1.DIMACSRutgers UniversityPiscatawayUSA
  2. 2.Central Economics-Mathematics InstituteMoscowRussia
  3. 3.Faculty of ManagementRutgers UniversityNewarkUSA
  4. 4.Department of PsychologyUniversity of IllinoisChampaignUSA

Personalised recommendations