Citation

Sakalauskas L. Methodology and Computing in Applied Probability 2010; 12(2): 247-259.

Copyright

(Copyright © 2010)

DOI

10.1007/s11009-009-9146-2

PMID

unavailable

Abstract

The paper considers numerical issues of the empirical Bayesian approach model, applied to estimation of small rates. The condition for non-singularity of Bayesian estimates is given and the convenient iterative algorithm for estimation is described. The clustering algorithm is also developed, using the property of Poisson-Gaussian model to treat probabilities of events in populations being the same, if the variance of probabilities is small. The approach considered is illustrated by an application to the analysis of homicides and suicides data in Lithuania, 2003-2004. © Springer Science+Business Media, LLC 2009.

Language: en

Keywords

Clustering; Empirical Bayesian; Maximal likelihood; Poisson-Gaussian model