Summary
The notion of ‘the most random partition of a finite set’ is defined and proposed as a null model in classification. A Hamming-type distance between two independent and most random partitions is used for justifying its randomness, and is used for testing this null hypothesis. The probability distribution of the distance is studied for the latter purpose.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Bock, H. H. (1996): Probabilistic aspects in classification, IFCS’96, Kobe, March 1996, Invited Lecture 5.
Ewens, W. J. (1990): Population genetics theory — the past and the future, In: Mathematical and Statistical Developments of Evolutionary Theory, Lessard, S. ed., NATO Adv. Sci. Inst. Ser. C-299, Kluwer, Dordrecht, 177–227.
Gordon, A. D. (1996): Cluster validation, IFCS’96, Kobe, March 1996, Invited Lecture 1.
Harada. M. and Sibuya, M. (1991): Effectiveness of the classification using Chernoff faces. Japanese Journal of Applied Statistics, 20. 39–48 (in Japanese).
Rand, W. M. (1971): Objective criteria for the evaluation of clustering methods, Journal of American Statistical Association, 66, 846–850.
Sibuya, M. (1992): Distance between random partitions of a finite set, In: Distancia ‘92, Joly, S. and Le Calvé, G. (eds.) 143–145, June 22–26, Rennes.
Sibuya, M. (1993a): A random clustering process, Ann. Inst. Statist. Math., 45, 459–465.
Sibuya, M. (1993b): Random partition of a finite set by cycles of permutation,. Japan Journal of Industrial and Applied Mathematics, 10, 69–84.
Sibuya, M. and Yamato, H. (1995): Characterization of some random partitions, Japan Journal of Industrial and Applied Mathematics, 12, 237–263.
Snijders, T. A. B. (1996): Private communications.
Zabell, S. L. (1992): Predicting the unpredictable, Syntheses, 90, 205–232.
Zahn. C. T., Jr. (1964): Approximating symmetric relations by equivalence relations, J. Soc. Indust. Appl. Math., 12, 840–847.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1998 Springer Japan
About this paper
Cite this paper
Sibuya, M. (1998). The Most Random Partition of a Finite Set and its Application to Classification. In: Hayashi, C., Yajima, K., Bock, HH., Ohsumi, N., Tanaka, Y., Baba, Y. (eds) Data Science, Classification, and Related Methods. Studies in Classification, Data Analysis, and Knowledge Organization. Springer, Tokyo. https://doi.org/10.1007/978-4-431-65950-1_25
Download citation
DOI: https://doi.org/10.1007/978-4-431-65950-1_25
Publisher Name: Springer, Tokyo
Print ISBN: 978-4-431-70208-5
Online ISBN: 978-4-431-65950-1
eBook Packages: Springer Book Archive