Model-Based Clustering, Discriminant Analysis, and Density Estimation Export

@article{fraley:raftery:2002, abstract = {Cluster analysis is the automated search for groups of related observations in a dataset. Most clustering done in practice is based largely on heuristic but intuitively reasonable procedures, and most clustering methods available in commercial software are also of this type. However, there is little systematic guidance associated with these methods for solving important practical questions that arise in cluster analysis, such as how many clusters are there, which clustering method should be used, and how should outliers be handled. We review a general methodology for model-based clustering that provides a principled statistical approach to these issues. We also show that this can be useful for other problems in multivariate analysis, such as discriminant analysis and multivariate density estimation. We give examples from medical diagnosis, minefield detection, cluster recovery from noisy data, and spatial density estimation. Finally, we mention limitations of the methodology and discuss recent developments in model-based clustering for non-Gaussian data, high-dimensional datasets, large datasets, and Bayesian estimation.}, author = {Fraley, C. and Raftery, A.}, citeulike-article-id = {781684}, citeulike-linkout-0 = {http://www.ingentaconnect.com/content/asa/jasa/2002/00000097/00000458/art00022}, citeulike-linkout-1 = {http://www.stat.washington.edu/www/research/reports/2000/tr380.ps}, journal = {Journal of the American Statistical Association}, keywords = {cluster\_analysis, em\_algorithm, multivariate}, month = {June}, number = {458}, pages = {611--631}, posted-at = {2006-08-01 14:40:46}, priority = {0}, title = {Model-Based Clustering, Discriminant Analysis, and Density Estimation}, url = {http://www.ingentaconnect.com/content/asa/jasa/2002/00000097/00000458/art00022}, volume = {97}, year = {2002} }

TY - JOUR ID - fraley:raftery:2002 L3 - citeulike-article-id:781684 N2 - Cluster analysis is the automated search for groups of related observations in a dataset. Most clustering done in practice is based largely on heuristic but intuitively reasonable procedures, and most clustering methods available in commercial software are also of this type. However, there is little systematic guidance associated with these methods for solving important practical questions that arise in cluster analysis, such as how many clusters are there, which clustering method should be used, and how should outliers be handled. We review a general methodology for model-based clustering that provides a principled statistical approach to these issues. We also show that this can be useful for other problems in multivariate analysis, such as discriminant analysis and multivariate density estimation. We give examples from medical diagnosis, minefield detection, cluster recovery from noisy data, and spatial density estimation. Finally, we mention limitations of the methodology and discuss recent developments in model-based clustering for non-Gaussian data, high-dimensional datasets, large datasets, and Bayesian estimation. IS - 458 JF - Journal of the American Statistical Association EP - 631 TI - Model-Based Clustering, Discriminant Analysis, and Density Estimation VL - 97 SP - 611 KW - cluster_analysis KW - em_algorithm KW - multivariate AU - Fraley, C AU - Raftery, A PY - 2002/06// UR - http://www.ingentaconnect.com/content/asa/jasa/2002/00000097/00000458/art00022 ER -