Estimation of a poisson mean using discrete mixtures of conjugate priors |
| |
Authors: | James H Albert |
| |
Institution: | Bowling Green State University and the University of Southampton , |
| |
Abstract: | The problem of estimating a Poisson mean is considered using incomplete prior information. The user is only able to assess two fractiles of the prior distribution. A class of mixture distributions is constructed to model this prior information; variation within this class primarily occurs in the tail region where little prior information exists. The posterior analysis using the mixture class is attractive computationally and compares favorably with the conjugate posterior analysis. |
| |
Keywords: | flat tails mixtures noninformative priors robustness shrinkage |
|