Bayesian inference with dependent normalized completely random measures (Q396004): Difference between revisions
From MaRDI portal
Created a new Item |
Changed an Item |
||
Property / author | |||
Property / author: Antonio Lijoi / rank | |||
Normal rank | |||
Property / author | |||
Property / author: Igor Prünster / rank | |||
Normal rank | |||
Property / review text | |||
In the context of Bayesian inference, the authors introduce a flexible class of dependent nonparametric priors, investigate their properties and derive a sampling scheme for their implementation. The construction of the class relies on normalizing dependent completely random measures (CRM), where the dependence is created at the level of the underlying Poisson random measures (PRM). The authors provide general distributional results for the whole class of dependent CRMs and then consider analytically tractable specific priors: the bivariate Dirichlet and normalized \(\sigma\)-stable processes. The obtained analytical results form the basis for the determination of a Markov chain Monte Carlo algorithm for drawing posterior inferences, which reduces to Blackwell-MacQueen Pólya urn scheme in the univariate case. The algorithm can be used for density estimation and for analyzing the clustering structure of the data. It is illustrated through a real two-sample dataset example. | |||
Property / review text: In the context of Bayesian inference, the authors introduce a flexible class of dependent nonparametric priors, investigate their properties and derive a sampling scheme for their implementation. The construction of the class relies on normalizing dependent completely random measures (CRM), where the dependence is created at the level of the underlying Poisson random measures (PRM). The authors provide general distributional results for the whole class of dependent CRMs and then consider analytically tractable specific priors: the bivariate Dirichlet and normalized \(\sigma\)-stable processes. The obtained analytical results form the basis for the determination of a Markov chain Monte Carlo algorithm for drawing posterior inferences, which reduces to Blackwell-MacQueen Pólya urn scheme in the univariate case. The algorithm can be used for density estimation and for analyzing the clustering structure of the data. It is illustrated through a real two-sample dataset example. / rank | |||
Normal rank | |||
Property / reviewed by | |||
Property / reviewed by: Pavel Stoynov / rank | |||
Normal rank | |||
Property / Mathematics Subject Classification ID | |||
Property / Mathematics Subject Classification ID: 60G57 / rank | |||
Normal rank | |||
Property / Mathematics Subject Classification ID | |||
Property / Mathematics Subject Classification ID: 62F15 / rank | |||
Normal rank | |||
Property / zbMATH DE Number | |||
Property / zbMATH DE Number: 6327909 / rank | |||
Normal rank | |||
Property / zbMATH Keywords | |||
completely random measure | |||
Property / zbMATH Keywords: completely random measure / rank | |||
Normal rank | |||
Property / zbMATH Keywords | |||
dependent Poisson processes | |||
Property / zbMATH Keywords: dependent Poisson processes / rank | |||
Normal rank | |||
Property / zbMATH Keywords | |||
Dirichlet process | |||
Property / zbMATH Keywords: Dirichlet process / rank | |||
Normal rank | |||
Property / zbMATH Keywords | |||
generalized Pólya urn scheme | |||
Property / zbMATH Keywords: generalized Pólya urn scheme / rank | |||
Normal rank | |||
Property / zbMATH Keywords | |||
infinitely divisible vector | |||
Property / zbMATH Keywords: infinitely divisible vector / rank | |||
Normal rank | |||
Property / zbMATH Keywords | |||
normalized \(\sigma\)-stable process | |||
Property / zbMATH Keywords: normalized \(\sigma\)-stable process / rank | |||
Normal rank | |||
Property / zbMATH Keywords | |||
partially exchangeable random partition | |||
Property / zbMATH Keywords: partially exchangeable random partition / rank | |||
Normal rank |
Revision as of 16:18, 29 June 2023
scientific article
Language | Label | Description | Also known as |
---|---|---|---|
English | Bayesian inference with dependent normalized completely random measures |
scientific article |
Statements
Bayesian inference with dependent normalized completely random measures (English)
0 references
8 August 2014
0 references
In the context of Bayesian inference, the authors introduce a flexible class of dependent nonparametric priors, investigate their properties and derive a sampling scheme for their implementation. The construction of the class relies on normalizing dependent completely random measures (CRM), where the dependence is created at the level of the underlying Poisson random measures (PRM). The authors provide general distributional results for the whole class of dependent CRMs and then consider analytically tractable specific priors: the bivariate Dirichlet and normalized \(\sigma\)-stable processes. The obtained analytical results form the basis for the determination of a Markov chain Monte Carlo algorithm for drawing posterior inferences, which reduces to Blackwell-MacQueen Pólya urn scheme in the univariate case. The algorithm can be used for density estimation and for analyzing the clustering structure of the data. It is illustrated through a real two-sample dataset example.
0 references
completely random measure
0 references
dependent Poisson processes
0 references
Dirichlet process
0 references
generalized Pólya urn scheme
0 references
infinitely divisible vector
0 references
normalized \(\sigma\)-stable process
0 references
partially exchangeable random partition
0 references