×

Model-based classification via mixtures of multivariate \(t\)-factor analyzers. (English) Zbl 1294.62142

Summary: A model-based classification technique is developed, based on mixtures of multivariate \(t\)-factor analyzers. Specifically, two related mixture models are developed and their classification efficacy studied. An AECM algorithm is used for parameter estimation, and convergence of these algorithms is determined using Aitken’s acceleration. Two different techniques are proposed for model selection: the BIC and the ICL. Our classification technique is applied to data on red wine samples from Italy and to fatty acid measurements on Italian olive oils. These results are discussed and compared to more established classification techniques; under this comparison, our mixture models give excellent classification performance.

MSC:

62H30 Classification and discrimination; cluster analysis (statistical aspects)
62H25 Factor analysis and principal components; correspondence analysis

Software:

mclust; R
PDF BibTeX XML Cite
Full Text: DOI

References:

[1] Aitken A. C., Proc. Roy. Soc. Edinburgh 46 pp 289– (1926)
[2] DOI: 10.1007/s11222-010-9175-2
[3] DOI: 10.1016/j.jspi.2010.10.014 · Zbl 1204.62098
[4] DOI: 10.1016/j.csda.2010.05.019 · Zbl 1247.62151
[5] DOI: 10.1080/01621459.1996.10476746
[6] DOI: 10.1109/34.865189
[7] DOI: 10.1016/0031-3203(94)00125-6 · Zbl 05480211
[8] DOI: 10.1111/j.1467-9876.2005.00526.x · Zbl 1490.62155
[9] Dempster A. P., J. Roy. Statist. Soc. Ser. B 39 (1) pp 1– (1977)
[10] DOI: 10.1111/j.1469-1809.1936.tb02137.x
[11] Forina M., Food Research and Data Analysis pp 189– (1983)
[12] Forina M., Vitis 25 pp 189– (1986)
[13] DOI: 10.1198/016214502760047131 · Zbl 1073.62545
[14] Fraley , C. , Raftery , A. E. ( 2006 ). MCLUST version 3 for R: Normal mixture modeling and model-based clustering.Technical Report 504, Department of Statistics, University of Washington, minor revisions January 2007 and November 2007 .
[15] DOI: 10.1080/01621459.1989.10478752
[16] Frühwirth-Schnatter S., Finite Mixture and Markov Switching Models (2006)
[17] Fukunaga K., Introduction to Statistical Pattern Recognition., 2. ed. (1990) · Zbl 0711.62052
[18] Ghahramani , Z. , Hinton , G. E. ( 1997 ). The EM algorithm for factor analyzers.Tech. Rep. CRG-TR-96-1, University of Toronto, Toronto .
[19] DOI: 10.1007/BF01908075
[20] DOI: 10.1198/106186004X12425
[21] Lindsay , B. G. ( 1995 ). Mixture models: Theory, geometry and applications.NSF-CBMS Regional Conference Series in Probability and Statistics.Vol. 5, Hayward, CA: Institute of Mathematical Statistics . · Zbl 1163.62326
[22] McLachlan , G. J. , Peel , D. ( 1998 ). Robust cluster analysis via mixtures of multivariatet-distributions. Lecture Notes in Computer Science. Vol. 1451. Berlin: Springer-Verlag, pp. 658–666 .
[23] DOI: 10.1002/0471721182
[24] McLachlan G. J., Seventh Int. Confer. Mach. Learn. pp 599– (2000)
[25] DOI: 10.1093/bioinformatics/18.3.413
[26] DOI: 10.1016/S0167-9473(02)00183-4 · Zbl 1256.62036
[27] DOI: 10.1016/j.csda.2006.09.015 · Zbl 1445.62053
[28] DOI: 10.1007/s11222-008-9056-0
[29] DOI: 10.1016/j.jspi.2009.11.006 · Zbl 1181.62095
[30] DOI: 10.1093/bioinformatics/btq498
[31] DOI: 10.1016/j.csda.2009.02.011 · Zbl 1464.62131
[32] DOI: 10.1111/1467-9868.00082
[33] DOI: 10.1093/biomet/80.2.267 · Zbl 0778.62022
[34] DOI: 10.1023/A:1008981510081
[35] DOI: 10.1198/016214506000000113 · Zbl 1118.62339
[36] Raftery A. E., Statistics in the 21st Century (2002) · Zbl 1007.62088
[37] DOI: 10.1080/01621459.1971.10482356
[38] R: A Language and Environment for Statistical Computing (2010)
[39] DOI: 10.1214/aos/1176344136 · Zbl 0379.62005
[40] DOI: 10.1007/s11222-009-9138-7
[41] Steane , M. A. ( 2009 ).Model-Based Classification via Mixtures of Multivariate t-Factor Analyzers.Master’s thesis, University of Guelph, Guelph, Ontario .
[42] Swayne , D. , Cook , D. , Buja , A. , Lang , D. , Wickhan , H. , Lawrence , M. ( 2006 ). GGobi Manual. www.ggobi.org/docs/manual.pdf.
[43] DOI: 10.1007/978-0-387-21706-2
[44] Wolfe , J. H. ( 1963 ). Object Cluster Analysis of Social Areas. Master’s thesis, University of California, Berkeley .
[45] Woodbury , M. A. ( 1950 ). Inverting Modified Matrices. Statistical Research Group, Memorandum Report 42, Princeton University, Princeton, NJ .
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.