论文信息 - An EM algorithm for a mixture model of count data

An EM algorithm for a mixture model of count data

An EM-algorithm is proposed to study a mixture model for the analysis of count data. Iterative procedures for estimating the parameters are given for various discrete distributions including Binomial, Negative Binomial, and Poisson. The EM procedure is applied to a set of PVC data in Berry (1987).

Daniel Y. T. Fong | Paul S. F. Yip | P. Yip | D. Y. Fong

[1] D. A. Sprott,et al. The use of a mixture model in the analysis of count data. , 1988, Biometrics.

[2] D A Berry,et al. Logarithmic transformations in ANOVA. , 1987, Biometrics.

[3] T. Louis. Finding the Observed Information Matrix When Using the EM Algorithm , 1982 .

[4] H. Sather,et al. A comparison of tests of the difference in the proportion of patients who are cured. , 1992, Biometrics.

[5] Paul Yip,et al. INFERENCE ABOUT THE MEAN OF A POISSON DISTRIBUTION IN THE PRESENCE OF A NUISANCE PARAMETER , 1988 .

[6] Paul S. F. Yip,et al. Conditional inference on a mixture model for the analysis of count data , 1991 .