Nonparametric Bayesian models through probit stick-breaking processes.
Journal Article (Journal Article)
We describe a novel class of Bayesian nonparametric priors based on stick-breaking constructions where the weights of the process are constructed as probit transformations of normal random variables. We show that these priors are extremely flexible, allowing us to generate a great variety of models while preserving computational simplicity. Particular emphasis is placed on the construction of rich temporal and spatial processes, which are applied to two problems in finance and ecology.
Full Text
Duke Authors
Cited Authors
- Rodríguez, A; Dunson, DB
Published Date
- March 2011
Published In
Volume / Issue
- 6 / 1
PubMed ID
- 24358072
Pubmed Central ID
- PMC3865248
Electronic International Standard Serial Number (EISSN)
- 1931-6690
International Standard Serial Number (ISSN)
- 1936-0975
Digital Object Identifier (DOI)
- 10.1214/11-ba605
Language
- eng