On a Proper Bayes, but Inadmissible Estimator

dc.contributor.author	BHAGWAT, PANKAJ	en_US
dc.contributor.author	Marchand, Eric	en_US
dc.date.accessioned	2019-07-24T07:05:52Z
dc.date.available	2019-07-24T07:05:52Z
dc.date.issued	2019-05	en_US
dc.identifier.citation	American Statistician.	en_US
dc.identifier.issn	0003-1305	en_US
dc.identifier.issn	1537-2731	en_US
dc.identifier.uri	http://dr.iiserpune.ac.in:8080/xmlui/handle/123456789/3770
dc.identifier.uri	https://doi.org/10.1080/00031305.2019.1604432	en_US
dc.description.abstract	We present an example of a proper Bayes point estimator which is inadmissible. It occurs for a negative binomial model with shape parameter a, probability parameter p, prior densities of the form π(a,p) = β g(a) (1−p)β−1, and for estimating the population mean μ=a(1−p)/p under squared error loss. Other intriguing features are exhibited such as the constancy of the Bayes estimator with respect to the choice of g, including degenerate or known a cases.	en_US
dc.language.iso	en	en_US
dc.publisher	Taylor & Francis	en_US
dc.subject	Bayes estimator	en_US
dc.subject	Inadmissibility	en_US
dc.subject	Negative binomial	en_US
dc.subject	TOC-JUL-2019	en_US
dc.subject	2019	en_US
dc.title	On a Proper Bayes, but Inadmissible Estimator	en_US
dc.type	Article	en_US
dc.contributor.department	Dept. of Mathematics	en_US
dc.identifier.sourcetitle	American Statistician.	en_US
dc.publication.originofpublisher	Foreign	en_US