File Download
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1214/09-BA407
- Scopus: eid_2-s2.0-79952597899
- WOS: WOS:000273483400001
- Find via
Supplementary
-
Bookmarks:
- CiteULike: 1
- Citations:
- Appears in Collections:
Article: Bayesian generalized method of moments
Title | Bayesian generalized method of moments |
---|---|
Authors | |
Keywords | Bayesian inference Correlated data Estimation efficiency Generalized estimating equation Generalized linear model |
Issue Date | 2009 |
Publisher | International Society for Bayesian Analysis. The Journal's web site is located at http://ba.stat.cmu.edu/ |
Citation | Bayesian Analysis, 2009, v. 4 n. 2, p. 191-208 How to Cite? |
Abstract | We propose the Bayesian generalized method of moments (GMM), which is particularly useful when likelihood-based methods are di±cult. By de-riving the moments and concatenating them together, we build up a weighted quadratic objective function in the GMM framework. As in a normal density function, we take the negative GMM quadratic function divided by two and ex-ponentiate it to substitute for the usual likelihood. After specifying the prior dis-tributions, we apply the Markov chain Monte Carlo procedure to sample from the
posterior distribution. We carry out simulation studies to examine the proposed Bayesian GMM procedure, and illustrate it with a real data example. |
Persistent Identifier | http://hdl.handle.net/10722/139730 |
ISSN | 2023 Impact Factor: 4.9 2023 SCImago Journal Rankings: 1.761 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Yin, G | en_US |
dc.date.accessioned | 2011-09-23T05:54:49Z | - |
dc.date.available | 2011-09-23T05:54:49Z | - |
dc.date.issued | 2009 | en_US |
dc.identifier.citation | Bayesian Analysis, 2009, v. 4 n. 2, p. 191-208 | en_US |
dc.identifier.issn | 1931-6690 | - |
dc.identifier.uri | http://hdl.handle.net/10722/139730 | - |
dc.description.abstract | We propose the Bayesian generalized method of moments (GMM), which is particularly useful when likelihood-based methods are di±cult. By de-riving the moments and concatenating them together, we build up a weighted quadratic objective function in the GMM framework. As in a normal density function, we take the negative GMM quadratic function divided by two and ex-ponentiate it to substitute for the usual likelihood. After specifying the prior dis-tributions, we apply the Markov chain Monte Carlo procedure to sample from the posterior distribution. We carry out simulation studies to examine the proposed Bayesian GMM procedure, and illustrate it with a real data example. | - |
dc.language | eng | en_US |
dc.publisher | International Society for Bayesian Analysis. The Journal's web site is located at http://ba.stat.cmu.edu/ | en_US |
dc.relation.ispartof | Bayesian Analysis | en_US |
dc.rights | © 2009 International Society for Bayesian Analysis. This article is available online at https://doi.org/10.1214/09-BA407 | - |
dc.subject | Bayesian inference | - |
dc.subject | Correlated data | - |
dc.subject | Estimation efficiency | - |
dc.subject | Generalized estimating equation | - |
dc.subject | Generalized linear model | - |
dc.title | Bayesian generalized method of moments | en_US |
dc.type | Article | en_US |
dc.identifier.email | Yin, G: gyin@hku.hk | en_US |
dc.identifier.authority | Yin, G=rp00831 | en_US |
dc.description.nature | published_or_final_version | - |
dc.identifier.doi | 10.1214/09-BA407 | - |
dc.identifier.scopus | eid_2-s2.0-79952597899 | - |
dc.identifier.hkuros | 195701 | en_US |
dc.identifier.volume | 4 | en_US |
dc.identifier.issue | 2 | en_US |
dc.identifier.spage | 191 | en_US |
dc.identifier.epage | 208 | en_US |
dc.identifier.isi | WOS:000273483400001 | - |
dc.identifier.citeulike | 11835148 | - |
dc.identifier.issnl | 1931-6690 | - |