Show simple item record

dc.contributor.authorWoteki, Thomas H.en
dc.date.accessioned2021-10-15T20:57:41Zen
dc.date.available2021-10-15T20:57:41Zen
dc.date.issued1974en
dc.identifier.urihttp://hdl.handle.net/10919/105397en
dc.description.abstractGiven a G-invariant family of distributions and under suitable hypotheses concerning G, we characterize the form of G-equivariant estimators. In fact, corresponding to each G-equivariant estimator is an appropriate G-invariant function and conversely. In the course of characterizing the G-equivariant estimators, we obtain two maximal invariant functions. Some properties of these functions are obtained and in particular we calculate their densities with respect to an appropriate Haar measure. Finally, we consider an invariant estimator problem, the problem of estimating the orbit of a parameter. It is seen that this invariant problem may be referred back to an equivariant one. A loss function for the invariant problem is defined in such a way that the minimumr risk invariant estimator corresponds to the minimumr risk equivariant estimator within a subclass of all equivariant estimators.en
dc.format.extentiv, 70 leavesen
dc.format.mimetypeapplication/pdfen
dc.language.isoenen
dc.publisherVirginia Polytechnic Institute and State Universityen
dc.relation.isformatofOCLC# 34239029en
dc.rightsIn Copyrighten
dc.rights.urihttp://rightsstatements.org/vocab/InC/1.0/en
dc.subject.lccLD5655.V856 1974.W67en
dc.titleEquivariant estimators and a special group structureen
dc.typeDissertationen
dc.contributor.departmentStatisticsen
dc.description.degreePh. D.en
thesis.degree.namePh. D.en
thesis.degree.leveldoctoralen
thesis.degree.grantorVirginia Polytechnic Institute and State Universityen
thesis.degree.disciplineStatisticsen
dc.type.dcmitypeTexten


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record