Improving the EM Algorithm
暂无分享,去创建一个
SUMMARY A modification of the EM algorithm is proposed for situations in which the maximization of the "complete data" likelihood function does not have a closed-form solution. Self-consistency of the modified algorithm is established. Application to carcinogenicity experiments is illustrated, and the results of a simulation study comparing the original and modified versions indicate that use of the proposed modification can lead to significant computational savings.
[1] D. Cox,et al. Analysis of Survival Data. , 1985 .
[2] D. Rubin,et al. Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .
[3] B. Jørgensen. The Delta Algorithm and GLIM , 1984 .
[4] J D Kalbfleisch,et al. Nonparametric methods for survival/sacrifice experiments. , 1986, Biometrics.