Variational Inference for Heteroscedastic Semiparametric Regression

Menictas, M; Wand, MP

Variational Inference for Heteroscedastic Semiparametric Regression

Menictas, M Wand, MP

Permalink

Publication Type:: Journal Article
Citation:: Australian and New Zealand Journal of Statistics, 2015, 57 (1), pp. 119 - 138
Issue Date:: 2015-01-01

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Unknown

Download Published VersionUnknown (886.95 kB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Menictas, M	en_US
dc.contributor.author	Wand, MP https://orcid.org/0000-0003-2555-896X	en_US
dc.date.issued	2015-01-01	en_US
dc.identifier.citation	Australian and New Zealand Journal of Statistics, 2015, 57 (1), pp. 119 - 138	en_US
dc.identifier.issn	1369-1473	en_US
dc.identifier.uri	http://hdl.handle.net/10453/41187
dc.description.abstract	© 2015 Australian Statistical Publishing Association Inc. We develop fast mean field variational methodology for Bayesian heteroscedastic semiparametric regression, in which both the mean and variance are smooth, but otherwise arbitrary, functions of the predictors. Our resulting algorithms are purely algebraic, devoid of numerical integration and Monte Carlo sampling. The locality property of mean field variational Bayes implies that the methodology also applies to larger models possessing variance function components. Simulation studies indicate good to excellent accuracy, and considerable time savings compared with Markov chain Monte Carlo. We also provide some illustrations from applications.	en_US
dc.relation	http://purl.org/au-research/grants/arc/DP110100061
dc.relation.ispartof	Australian and New Zealand Journal of Statistics	en_US
dc.relation.isbasedon	10.1111/anzs.12105	en_US
dc.subject.classification	Statistics & Probability	en_US
dc.title	Variational Inference for Heteroscedastic Semiparametric Regression	en_US
dc.type	Journal Article
utslib.citation.volume	1	en_US
utslib.citation.volume	57	en_US
utslib.for	0104 Statistics	en_US
utslib.for	1403 Econometrics	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Science
pubs.organisational-group	/University of Technology Sydney/Faculty of Science/School of Mathematical and Physical Sciences
utslib.copyright.status	open_access
pubs.issue	1	en_US
pubs.publication-status	Published	en_US
pubs.volume	57	en_US

Abstract:

© 2015 Australian Statistical Publishing Association Inc. We develop fast mean field variational methodology for Bayesian heteroscedastic semiparametric regression, in which both the mean and variance are smooth, but otherwise arbitrary, functions of the predictors. Our resulting algorithms are purely algebraic, devoid of numerical integration and Monte Carlo sampling. The locality property of mean field variational Bayes implies that the methodology also applies to larger models possessing variance function components. Simulation studies indicate good to excellent accuracy, and considerable time savings compared with Markov chain Monte Carlo. We also provide some illustrations from applications.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/41187