Bayesian and Non-Bayesian Tests of Independence in Seemingly Unrelated Regressions

Tsunemasa Shiba and Hiroki Tsurumi

International Economic Review, 1988, vol. 29, issue 2, 377-95

Abstract: Bayesian and non-Bayesian statistics are derived for testing whether or not two blocks of seemingly unrelated regressions are independent. The non-Bayesian statistics are the likelihood ratio test (LRT), Wald's test (WT), and the Lagrange multiplier test (LMT). The authors interpret the LMT and WT as differences in the log of likelihoods conditioned on estimates of nuisance parameters. The Bayesian test is a highest posterior density region test that can also be derived as a Bayes factor. The four tests are compared in sampling experiments. Copyright 1988 by Economics Department of the University of Pennsylvania and the Osaka University Institute of Social and Economic Research Association.

Date: 1988
References: Add references at CitEc
Citations: View citations in EconPapers (5)

Downloads: (external link)
http://links.jstor.org/sici?sici=0020-6598%2819880 ... O%3B2-O&origin=repec full text (application/pdf)
Access to full text is restricted to JSTOR subscribers. See http://www.jstor.org for details.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:ier:iecrev:v:29:y:1988:i:2:p:377-95

Ordering information: This journal article can be ordered from
http://www.blackwell ... bs.asp?ref=0020-6598

Access Statistics for this article

International Economic Review is currently edited by Harold L. Cole

More articles in International Economic Review from Department of Economics, University of Pennsylvania and Osaka University Institute of Social and Economic Research Association 160 McNeil Building, 3718 Locust Walk, Philadelphia, PA 19104-6297. Contact information at EDIRC.
Bibliographic data for series maintained by Wiley-Blackwell Digital Licensing () and ().