Abstract
We review methods of qualitative factor analysis (QFA) developed by the author and his collaborators over the last decade and discuss the use of QFA methods for the additive clustering problem. The QFA method includes, first, finding a square Boolean matrix in a fixed set of Boolean matrices with “simple structures” to approximate a given similarity matrix, and, second, repeating this process again and again using residual similarity matrices. We present convergence properties for three versions of the method, provide “cluster” interpretations for results obtained from the algorithms, and give formulas for the evaluation of “factor shares” of the initial similarities variance.
Similar content being viewed by others
References
ARABIE, P., BOORMAN, S. A., and LEVITT, P. R. (1978), “Constructing Block Models: How and Why,”Journal of Mathematical Psychology, 17, 21–63.
ARABIE, P., and CARROLL, J. D. (1980), “MAPCLUS: A Mathematical Programming Approach to Fitting the ADCLUS Model,”Psychometrika, 45, 211–235.
ARABIE, P., CARROLL, J. D., DeSARBO, W., and WIND, J. (1981), “Overlapping Clustering: A New Method for Product Positioning,”Journal of Marketing Research, 18, 310–317.
BORODKIN, A. M., KRIEGMAN, I. E., MUCHNIK, I. B., and TELKOV, U. K. (1978), “Revealing of Design Jobs Set for Purposes of Design Automatization,”Automation and Remote Control, 5, 97–105 (in Russian). “Identification of Industrial-design Activities for Computerization,”Automation and Remote Control, 39, 5, 701–708 (in English).
BORODKIN, A. M., and MUCHNIK, I. B. (1977), “Approximate Algorithm Based on Second Increments Method for the Problem of Approximation of Graphs,”Automation and Remote Control, 4, 114–120 (in Russian). “An Approximate Algorithm for Graph Approximations Based on the Method of Second Difference,”Automation and Remote Control, 38, 4, Part 2, 548–553 (in English).
BREIGER, R. L., BOORMAN, S. A., and ARABIE, P. (1975), “An Algorithm for Clustering Relational Data with Applications to Social Network Analysis and Comparison with Multidimensional Scalling,”Journal of Mathematical Psychology, 12, 328–383.
CARROLL, J. D., and ARABIE, P. (1983), “INDCLUS: An Individual Differences Generalization of the ADCLUS Model and the MAPCLUS Algorithm,”Psychometrika, 48, 157–169.
HARMAN, H. H. (1960),Modern Factor Analysis, Chicago: University of Chicago Press.
KUPERSHTOKH, W. L. (1976), “On Threshold of Significance of Proximities in Classification Problem,” InProblems of Discrete Data Analysis, ed. B. G. Mirkin, Novosibirsk, 70–74 (in Russian).
KUPERSHTOKH, W. L., MIRKIN, B. G., and TROFIMOV, W. A. (1976a), “Least Squares Method in Qualitative Variables Analysis,” InProblems of Discrete Data Analysis, ed. B. G. Mirkin, Novisibirsk, 4–23 (in Russian).
KUPERSHTOKH, W. L., MIRKIN, B. G., and TROFIMOV, W. A. (1976b), “Sum of Internal Proximities as a Criterion of Classification Quality,”Automation and Remote Control, 3, 91–98 (in Russian). “The Sum of Internal Couplings as an Index of Classification Quality,”Automation and Remote Control, 37, 3, Part 2, 548–553 (in English).
MIRKIN, B. G. (1974), “Approximation Problems in Space of Binary Relations and Nonquantitative Variables Analysis,”Automation and Remote Control, 51–61 (in Russian). “Approximation Problems in a Relative Space and the Analysis of Nonnumeric Methods,”Automation and Remote Control, 35, 9, Part 2, 1424–1431 (in English).
MIRKIN, B. G. (1976),Analysis of Qualitative Variables, Moscow: Statistika Publishers (in Russian).
MIRKIN, B. G. (1980),Analysis of Qualitative Attributes and Structures, Moscow: Statistika Publishers (in Russian).
MIRKIN, B. G. (1985).Classifications in Social and Economic Research, Moscow: Finansy and Statistika Publishers (in Russian).
MIRKIN, B. G., KUPERSHTOKH, W. L., and TROFIMOV, W. A. (1979), “On Models of Discrete Data Aggregation,” InMathematical Models and Methods in Economics Study, eds. L. E. Bierland and B. G. Mirkin, Novosibirsk, 158–214 (in Russian).
MIRKIN, B. G., and RODIN, S. N. (1977),Graphs and Genes, Moscow, 1977 (English translation: Springer-Verlag, 1984).
MIRKIN, B. G., and ROSTOVTSEV, P. S. (1978), “A Method for Revealing of Associated Sets of Variables,” InModels of Social and Economics Data Aggregation, ed. B. G. Mirkin, Novosibirsk, 107–112 (in Russian).
ROETHLISBERGER, F. J., and DICKSON, W. J. (1939),Management and the Worker, Cambridge, Mass.: Harvard University Press.
SHEPARD, R. N., and ARABIE, P. (1979), “Additive Clustering: Representation of Similarities as Combinations of Discrete Overlapping Properties,”Psychological Review, 86, 2, 87–123.
TROFIMOV, W. A. (1976), “Models and Methods of Qualitative Factor Analysis for Proximity Matrices,” InProblems of Discrete Data Analysis, ed. B. G. Mirkin, Novosibirsk, 24–35 (in Russian).
TROFIMOV, W. A. (1981a), “A Finite Method of Qualitative Factor Analysis,” InMethods of Multidimensional Economics Data Analysis, ed. B. G. Mirkin, Novosibirsk, 12–29 (in Russian).
TROFIMOV, V. A. (1981b), “Experimental Base of Qualitative Factor Analysis Methods,” InMethods of Multidimensional Economics Data Analysis, ed. B. G. Mirkin, Novosibirsk, 30–48 (in Russian).
Author information
Authors and Affiliations
Additional information
I am indebted to Professor P. Arabie and the referees for valuable comments and editing of the text.
Rights and permissions
About this article
Cite this article
Mirkin, B.G. Additive clustering and qualitative factor analysis methods for similarity matrices. Journal of Classification 4, 7–31 (1987). https://doi.org/10.1007/BF01890073
Issue Date:
DOI: https://doi.org/10.1007/BF01890073