Please use this identifier to cite or link to this item:
https://hdl.handle.net/20.500.14279/9853
Title: | Comparing distributions by using dependent normalized random-measure mixtures | Authors: | Griffin, Jim E. Kolossiatis, Michalis Steel, Mark F J |
Major Field of Science: | Natural Sciences | Field Category: | Mathematics | Keywords: | Bayesian non-parametrics;Dependent distributions;Dirichlet process;Normalized generalized gamma process;Slice sampling;Utility function | Issue Date: | 7-Feb-2013 | Source: | Journal of the Royal Statistical Society, Series B: Statistical Methodology, 2013, vol. 75, no. 3, pp. 499-529 | Volume: | 75 | Issue: | 3 | Start page: | 499 | End page: | 529 | Journal: | Journal of the Royal Statistical Society, Series B: Statistical Methodology | Abstract: | A methodology for the simultaneous Bayesian non-parametric modelling of several distributions is developed. Our approach uses normalized random measures with independent increments and builds dependence through the superposition of shared processes. The properties of the prior are described and the modelling possibilities of this framework are explored in detail. Efficient slice sampling methods are developed for inference. Various posterior summaries are introduced which allow better understanding of the differences between distributions. The methods are illustrated on simulated data and examples from survival analysis and stochastic frontier analysis. | URI: | https://hdl.handle.net/20.500.14279/9853 | ISSN: | 13697412 | DOI: | 10.1111/rssb.12002 | Rights: | © Royal Statistical Society. | Type: | Article | Affiliation : | University of Kent at Canterbury Cyprus University of Technology University of Warwick |
Publication Type: | Peer Reviewed |
Appears in Collections: | Άρθρα/Articles |
CORE Recommender
SCOPUSTM
Citations
27
checked on Nov 9, 2023
WEB OF SCIENCETM
Citations
5
26
Last Week
0
0
Last month
1
1
checked on Oct 29, 2023
Page view(s)
421
Last Week
0
0
Last month
1
1
checked on Nov 6, 2024
Google ScholarTM
Check
Altmetric
Items in KTISIS are protected by copyright, with all rights reserved, unless otherwise indicated.