Abstract
This paper formulates a novel expectation maximization (EM) algorithm for the mixture of multivariate t-distributions. By introducing a new kind of “missing” data, we show that the empirically improved iterative algorithm, in literature, for the mixture of multivariate t-distributions is in fact a type of EM algorithm; thus a theoretical analysis is established, which guarantees the empirical algorithm converges to the maximization likelihood estimates of the mixture parameters. Simulated experiment and real experiments on classification and image segmentation confirm the effectiveness of the improved EM algorithm.
References
Alfò M, Nieddu L, Vicari D (2008) A finite mixture model for image segmentation. Stat Comput 18: 137–150
Asuncion A, Newman DJ (2007) UCI Machine learning repository [http://www.ics.uci.edu/mlearn/MLRepository.html]. University of California, School of Information and Computer Science, Irvine, CA
Chen SB, Luo B (2004) Robust t-mixture modelling with SMEM algorithm. In: Proceedings of the third international conference on machine learning and cybernetics, vol. 6. Shanghai, China, pp 3689–3694
Chen S, Qin J (2006) An empirical likelihood method in mixture models with incomplete classifications. Stat Sinica 16: 1101–1115
Dempster AP, Laird NM, Rubin DB (1977) Maximum likelihood from incomplete data using the EM algorithm (with discussion). J R Stat Soc Ser B 39: 1–38
Di Zio M, Guarnera U, Luzi O (2007) Imputation through finite Gaussian mixture models. Comput Stat Data Anal 51: 5305–5316
Fonseca JRS, Cardoso MGMS (2007) Mixture-model cluster analysis using information theoretical criteria. Intell Data Anal 11: 155–173
Gerogiannis D, Nikou C, Likas A (2007) Robust image registration using mixtures of t-distributions. In: 11th IEEE international conference on computer vision, vol. 1–6. Rio de Janeiro, Brazil, pp 2330–2337
Ghahramani Z, Jordan MI (1994) Supervised learning from incomplete data via an EM approach. In: Cowan JD, Tesauro G, Alspector J (eds) Advances in neural information processing systems, vol 6. Morgan Kaufmann Publishers, San Francisco, CA, pp 120–127
Huang Z-K, Chau K-W (2008) A new image thresholding method based on Gaussian mixture model. Appl Math Comput 205: 899–907
Hunt LA, Jorgensen MA (2003) Mixture model clustering for mixed data with missing information. Comput Stat Data Anal 41: 429–440
Ibrahim J, Zhu H, Tang N (2008) Model selection criteria for missing-data problems using the EM algorithm. J Amer Stat Assoc 103: 1648–1658
Jain AK, Duin RPW, Mao J (2000) Statistical pattern recognition: a review. IEEE Trans Patt Anal Mach Intell 22: 4–37
Jiao S, Zhang S (2008) The t-mixture model approach for detecting differentially expressed genes in microarrays. Funct Integr Genomics 8: 181–186
Jolliffe IT (2002) Principal component analysis, 2nd edn. Springer, New York
Keribin C (2000) Consistent estimation of the order of mixture models. Sankhya Ser A 62: 49–66
Kroh M (2006) Taking “don’t knows” as valid responses: a multiple complete random imputation of missing data. Qual Quant 40: 225–244
Lange KL, Little RJA, Taylor JMG (1989) Robust statistical modeling using the t distribution. J Am Stat Assoc 84: 881–896
Lee Y, Hahn H, Han Y, Lee J (2005) Robust speaker identification based on t-distribution mixture model. Lect Notes Artif Intell 3809: 896–899
Li M, Zhang L (2008) Multinomial mixture model with feature selection for text clustering. Knowl-Based Syst 21: 704–708
Lin TI, Lee JC, Ni HF (2004) Bayesian analysis of mixture modelling using the multivariate t distribution. Stat Comput 14: 119–130
Liu C, Rubin DB, Wu YN (1998) Parameter expansion to accelerate EM: the PX-EM algorithm. Biometrika 85: 755–770
Lu Z, Peng Y (2008) A semi-supervised learning algorithm on gaussian mixture with automatic model selection. Neural Process Lett 27: 57–66
McLachlanz GJ, Bean RW, Jones LBT (2007) Extension of the mixture of factor analyzers model to incorporate the multivariate t-distribution. Comput Stat Data Anal 51: 5327–5338
McLachlan GJ, Bean RW, Peel D (2002) A mixture model-based approach to the clustering of microarray expression data. Bioinformatics 18: 413–422
McLachlan GJ, Peel D (2000) Finite mixture models. Wiley, New York
Meng XL, van Dyk D (1997) The EM algorithm-an old folk song sung to a fast new tune (with discussion). J R Stat Soc Ser B 59: 511–567
Morgan BJT, Ridout MS (2008) A new mixture model for capture heterogeneity. J R Stat Soc Ser C Appl Stat 57: 433–446
Paalanen P, Kamarainen J-K, Ilonen J, Kälviäinen H (2006) Feature representation and discrimination based on Gaussian mixture model probability densities—practices and algorithms. Pattern Recognit 39: 1346–1358
Peel D, McLachlan GJ (2000) Robust mixture modelling using the t distribution. Stat Comput 10: 339–348
Peng H, Zhu S (2007) Handling of incomplete data sets using ICA and SOM in data mining. Neural Comput Appl 16: 167–172
Rudas T (2005) Mixture models of missing data. Qual Quant 39: 19–36
Sahbi H (2008) A particular Gaussian mixture model for clustering and its application to image retrieval. Soft Comput 12: 667–676
Shoham S (2002) Robust clustering by deterministic agglomeration EM of mixtures of multivariate t distributions. Pattern Recognit 35: 1127–1142
Vellido A (2006) Missing data imputation through GTM as a mixture of t-distributions. Neural Netw 19: 1624–1635
Verbeke G, Molenberghs G, Beunckens C (2008) Formal and informal model selection with incomplete data. Stat Sci 23: 201–218
Wang H, Chen S, Hu Z, Luo B (2008) Probabilistic two-dimensional principal component analysis and its mixture model for face recognition. Neural Comput Appl 17: 541–547
Wang H, Zhang Q, Luo B, Wei S (2004) Robust mixture modelling using multivariate t-distribution with missing information. Pattern Recognit Lett 25: 701–710
Williams D, Liao X, Xue Y, Carin L, Krishnapuram B (2007) On classification with incomplete data. IEEE Trans Patt Anal Mach Intell 29: 427–436
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Wang, H., Hu, Z. On EM Estimation for Mixture of Multivariate t-Distributions. Neural Process Lett 30, 243–256 (2009). https://doi.org/10.1007/s11063-009-9121-5
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11063-009-9121-5