Bayesian inference on time-varying proportions

McCausland, WJ; Lgui, B

Bayesian inference on time-varying proportions

McCausland, WJ Lgui, B

Permalink

Publisher:: Emerald
Publication Type:: Chapter
Citation:: Bayesian Econometrics (Advances in Econometrics Vol 23), 2009, 1, pp. 525 - 544
Issue Date:: 2009-01

Closed Access

	Filename	Description	Size
	2010006476OK.pdf		1.54 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	McCausland, WJ	en_US
dc.contributor.author	Lgui, B	en_US
dc.contributor.editor	Chib, S	en_US
dc.contributor.editor	Griffiths, W	en_US
dc.contributor.editor	Koop, G	en_US
dc.contributor.editor	Terrell, D	en_US
dc.date.issued	2009-01	en_US
dc.identifier.citation	Bayesian Econometrics (Advances in Econometrics Vol 23), 2009, 1, pp. 525 - 544	en_US
dc.identifier.isbn	978-1-84855-308-8	en_US
dc.identifier.uri	http://hdl.handle.net/10453/17312
dc.description.abstract	Time-varying proportions arise frequently in economics. Market shares show the relative importance of firms in a market. Labor economists divide populations into different labor market segments. Expenditure shares describe how consumers and firms allocate total expenditure to various categories. We introduce a state space model where unobserved states are Gaussian and observations are conditionally Dirichlet. Markov chain Monte Carlo techniques allow inference for unknown parameters and states. We draw states as a block using a multivariate Gaussian proposal distribution based on a quadratic approximation of the log conditional density of states given parameters and data. Repeated draws from the proposal distribution are particularly efficient. We illustrate using automobile production data.	en_US
dc.publisher	Emerald	en_US
dc.relation.ispartof	Bayesian Econometrics (Advances in Econometrics Vol 23)	en_US
dc.relation.isbasedon	10.1016/S0731-9053(08)23016-1	en_US
dc.subject.classification	Econometrics	en_US
dc.title	Bayesian inference on time-varying proportions	en_US
dc.type	Chapter
utslib.location	USA	en_US
utslib.for	1403 Econometrics	en_US
utslib.citation.edition	1	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 Business
utslib.copyright.status	closed_access
pubs.consider-herdc	false	en_US
pubs.edition	1	en_US
pubs.place-of-publication	USA	en_US

Abstract:

Time-varying proportions arise frequently in economics. Market shares show the relative importance of firms in a market. Labor economists divide populations into different labor market segments. Expenditure shares describe how consumers and firms allocate total expenditure to various categories. We introduce a state space model where unobserved states are Gaussian and observations are conditionally Dirichlet. Markov chain Monte Carlo techniques allow inference for unknown parameters and states. We draw states as a block using a multivariate Gaussian proposal distribution based on a quadratic approximation of the log conditional density of states given parameters and data. Repeated draws from the proposal distribution are particularly efficient. We illustrate using automobile production data.

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

http://hdl.handle.net/10453/17312