Journal article
Characterizing variation of nonparametric random probability measures using the Kullback–Leibler divergence
- Abstract:
- This work characterizes the dispersion of some popular random probability measures, including the bootstrap, the Bayesian bootstrap, and the Pólya tree prior. This dispersion is measured in terms of the variation of the Kullback–Leibler divergence of a random draw from the process to that of its baseline centring measure. By providing a quantitative expression of this dispersion around the baseline distribution, our work provides insight for comparing different parameterizations of the models and for the setting of prior parameters in applied Bayesian settings. This highlights some limitations of the existing canonical choice of parameter settings in the Pólya tree process.
- Publication status:
- Published
- Peer review status:
- Peer reviewed
Actions
Access Document
- Files:
-
-
(Preview, Accepted manuscript, pdf, 466.2KB, Terms of use)
-
- Publisher copy:
- 10.1080/02331888.2016.1258072
Authors
+ Medical Research Council
More from this funder
- Funding agency for:
- Holmes, C
- Grant:
- MC_UP_A390_1107
+ Engineering and Physical Sciences Research Council
More from this funder
- Funding agency for:
- Holmes, C
- Grant:
- MC_UP_A390_1107
+ Asociación Mexicana de Cultura, A.C.–Mexico
More from this funder
- Funding agency for:
- Nieto-Barajas, L
- Grant:
- 244459
- Publisher:
- Taylor and Francis
- Journal:
- Statistics More from this journal
- Volume:
- 51
- Issue:
- 3
- Pages:
- 558-571
- Publication date:
- 2016-11-16
- Acceptance date:
- 2016-07-20
- DOI:
- EISSN:
-
1029-4910
- ISSN:
-
0233-1888
- Keywords:
- Pubs id:
-
pubs:664450
- UUID:
-
uuid:48f47373-28e0-49e8-9729-1251b764bd7a
- Local pid:
-
pubs:664450
- Source identifiers:
-
664450
- Deposit date:
-
2017-03-02
Terms of use
- Copyright holder:
- © 2016 Informa UK Limited, trading as Taylor & Francis Group
- Copyright date:
- 2016
- Notes:
- This is the author accepted manuscript following peer review version of the article. The final version is available online from Taylor & Francis at: 10.1080/02331888.2016.1258072
If you are the owner of this record, you can report an update to it here: Report update to this record