Estimation in Mixture of Shifted Poisson Distributions with Known Shift Parameters

Abstract

Suggested is an EM algorithm for estimation in mixture of shifted Poisson distributions with known shift parameters. For this type of mixture distribution, we have to utilize values of shift parameters to determine whether each of data belongs to some component distribution. We propose a method of estimating values of component information and then follow typical EM methodology. Simulation results show that the algorithm provides reasonable performance for the distribution.

Keywords

• 혼합 이동 포아송분포;
• EM 알고리즘;