Bayesian model-based clustering procedures

Amer Statistical Assoc
Publication Type:
Journal Article
Journal of Computational and Graphical Statistics, 2006, 16 (3), pp. 526 - 558
Issue Date:
Full metadata record
Files in This Item:
Filename Description SizeFormat
2010002256OK.pdf2.77 MBAdobe PDF
This paper establishes a general framework for Bayesian model-based clustering, in which subset labels are exchangeable, and items are also exchangeable, possibly up to covariate e®ects. It is rich enough to encompass a variety of existing procedures, including some recently discussed methodologies involving stochastic search or hierarchical clustering, but more importantly allows the formulation of clustering procedures that are optimal with respect to a speci¯ed loss function. Our focus is on loss functions based on pairwise coincidences, that is, whether pairs of items are clustered into the same subset or not.
Please use this identifier to cite or link to this item: