Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
1152250 | Statistics & Probability Letters | 2012 | 8 Pages |
Abstract
This paper considers generating exchangeable partition probability functions from an independent and identically distributed sample from a geometric distribution. We show that the model is rich and while different from exchangeable random variables based on nonparametric models, such as the Dirichlet process, both are driven by a single parameter, and hence to some extent comparable.
Related Topics
Physical Sciences and Engineering
Mathematics
Statistics and Probability
Authors
Ramsés H. Mena, Stephen G. Walker,