Nonparametric Bayes inference for concave distribution functions

Journal article

Bayesian inference for concave distribution functions is investigated. This is made by transforming a mixture of Dirichlet processes on the space of distribution functions to the space of concave distribution functions. We give a method for sampling from the posterior distribution using a Pólya urn scheme in combination with a Markov chain Monte Carlo algorithm. The methods are extended to estimation of concave distribution functions for incompletely observed data.

Authors: Hansen, M; Lauritzen, S

• Publication status: Published
• Journal: STATISTICA NEERLANDICA
• Volume: 56
• Issue: 1
• Pages: 110-127
• Publication date: 2002-02-01
• DOI: 10.1111/1467-9574.04600
• EISSN: 1467-9574
• ISSN: 0039-0402
• Language: English
• Keywords: Markov chain Monte Carlo; concave distribution functions; multiplicative censoring; Polya urn scheme; decreasing density function; Dirichlet process; order restdcted inference