EM and Beyond
- 1 June 1991
- journal article
- Published by Cambridge University Press (CUP) in Psychometrika
- Vol. 56 (2) , 241-254
- https://doi.org/10.1007/bf02294461
Abstract
The basic theme of the EM algorithm, to repeatedly use complete-data methods to solve incomplete data problems, is also a theme of several more recent statistical techniques. These techniques—multiple imputation, data augmentation, stochastic relaxation, and sampling importance resampling—combine simulation techniques with complete-data methods to attack problems that are difficult or impossible for EM.Keywords
This publication has 31 references indexed in Scilit:
- Using EM to Obtain Asymptotic Variance-Covariance Matrices: The SEM AlgorithmJournal of the American Statistical Association, 1991
- Multiple imputation in health‐are databases: An overview and some applicationsStatistics in Medicine, 1991
- Sampling-Based Approaches to Calculating Marginal DensitiesJournal of the American Statistical Association, 1990
- Imputation using markov chainsJournal of Statistical Computation and Simulation, 1988
- The Calculation of Posterior Distributions by Data AugmentationJournal of the American Statistical Association, 1987
- A Statistical Model for Positron Emission TomographyJournal of the American Statistical Association, 1985
- Estimation of Two-Parameter Logistic Item Response CurvesJournal of Educational Statistics, 1984
- On the Convergence Properties of the EM AlgorithmThe Annals of Statistics, 1983
- The Logistic Model and Estimation of Latent StructureJournal of the American Statistical Association, 1978
- Maximum Likelihood Estimation from Incomplete DataBiometrics, 1958