###
UNIFORM MIXTURES VIA POSTERIOR MEANS

###
ARJUN K. GUPTA^{ 1} AND JACEK WESOLOWSKI^{ 2}

^{1} *Department of Mathematics and Statistics, Bowling
Green State University,*

Bowling Green, OH 43403-0221, U.S.A.

^{2} *Mathematical Institute, Warsaw University of Technology,*

Plac Politechniki 1, 00-661 Warsaw, Poland
(Received June 5, 1995; revised February 19, 1996)

**Abstract.**
The problem of identification of uniform
mixtures via posterior means is studied. For linear posterior means
a complete solution is given. It determines a family of prior
distributions involving beta of both kinds and gamma.
Identifiability via any consistent posterior mean is also
investigated.

*Key words and phrases*:
Mixtures, posterior mean,
identification, characterization of probability distribution,
uniform conditional distribution, conditional moments, linearity of
regression, gamma distribution, beta type distributions.

**Source**
( TeX ,
DVI ,
PS )