Finding the Observed Information Matrix When Using the EM Algorithm
- 1 January 1982
- journal article
- research article
- Published by Oxford University Press (OUP) in Journal of the Royal Statistical Society Series B: Statistical Methodology
- Vol. 44 (2) , 226-233
- https://doi.org/10.1111/j.2517-6161.1982.tb01203.x
Abstract
A procedure is derived for extracting the observed information matrix when the EM algorithm is used to find maximum likelihood estimates in incomplete data problems. The technique requires computation of a complete‐data gradient vector or second derivative matrix, but not those associated with the incomplete data likelihood. In addition, a method useful in speeding up the convergence of the EM algorithm is developed. Two examples are presented.Keywords
This publication has 10 references indexed in Scilit:
- Approximate Posterior Distributions for Incomplete Data ProblemsJournal of the Royal Statistical Society Series B: Statistical Methodology, 1982
- Assessing the accuracy of the maximum likelihood estimator: Observed versus expected Fisher informationBiometrika, 1978
- Nonparametric Maximum Likelihood Estimation of a Mixing DistributionJournal of the American Statistical Association, 1978
- Screening for the early detection of cancer— III. Estimation of disease natural historyMathematical Biosciences, 1978
- Maximum Likelihood from Incomplete Data Via the EM AlgorithmJournal of the Royal Statistical Society Series B: Statistical Methodology, 1977
- An iterative method for solution of the likelihood equations for incomplete data from exponential familiesCommunications in Statistics - Simulation and Computation, 1976
- Nonparametric Estimation of a Survivorship Function with Doubly Censored DataJournal of the American Statistical Association, 1974
- A Rapidly Convergent Descent Method for MinimizationThe Computer Journal, 1963
- Maximum Likelihood Estimation from Incomplete DataBiometrics, 1958