ESTIMATING MEANS FROM A NON-I.I.D. MIXTURE
OF POISSON SAMPLES

STEVEN G. FROM

Department of Mathematics and Computer Science, University of Nebraska-Omaha,
Omaha, NB 68182-0243, U.S.A.

(Received May 23, 1989; revised May 15, 1990)

Abstract.    In this paper, a family of estimators for estimating means when mixing two independent Poisson samples is proposed. This family is based on the probability-generating function of the Poisson distribution and is offered as an alternative to the maximum likelihood estimators, which have some drawbacks. These estimators include the method of moments estimators as a special limiting case.

Key words and phrases:    Poisson distribution, probability-generating function, generalized variance.

Source ( TeX , DVI , PS )