A Monte Carlo Implementation of the EM Algorithm and the Poor Man's Data Augmentation Algorithms

Abstract The first part of this article presents the Monte Carlo implementation of the E step of the EM algorithm. Given the current guess to the maximizer of the posterior distribution, latent data patterns are generated from the conditional predictive distribution. The expected value of the augmented log-posterior is then updated as a mixture of augmented log-posteriors, mixed over the generated latent data patterns (multiple imputations). In the M step of the algorithm, this mixture is maximized to obtain the update to the maximizer of the observed posterior. The gradient and Hessian of the observed log posterior are also expressed as mixtures, mixed over the multiple imputations. The relation between the Monte Carlo EM (MCEM) algorithm and the data augmentation algorithm is noted. Two modifications to the MCEM algorithm (the poor man's data augmentation algorithms), which allow for the calculation of the entire posterior, are then presented. These approximations serve as diagnostics for the validity o...

[1]  H. Hartley.  Maximum Likelihood Estimation from Incomplete Data , 1958 .

[2]  Calyampudi Radhakrishna Rao,et al.  Linear Statistical Inference and its Applications , 1967 .

[3]  R. R. Hocking,et al.  The analysis of incomplete data. , 1971 .

[4]  G. C. Tiao,et al.  Bayesian inference in statistical analysis , 1973 .

[5]  Calyampudi R. Rao,et al.  Linear Statistical Inference and Its Applications. , 1975 .

[6]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[7]  G. J. Hahn,et al.  A Simple Method for Regression Analysis With Censored Data , 1979 .

[8]  Murray Aitkin,et al.  A Note on the Regression Analysis of Censored Data , 1981 .

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

[10]  R. A. Boyles.  On the Convergence of the EM Algorithm , 1983 .

[11]  New York Dover,et al.  ON THE CONVERGENCE PROPERTIES OF THE EM ALGORITHM , 1983 .

[12]  Donald Geman,et al.  Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  P. Diggle,et al.  Monte Carlo Methods of Inference for Implicit Statistical Models , 1984 .

[14]  D. Rubin.  Multiple imputation for nonresponse in surveys , 1989 .

[15]  Brian D. Ripley,et al.  Stochastic Simulation , 2005 .

[16]  W. Wong,et al.  The calculation of posterior distributions by data augmentation , 1987 .

[17]  R. Fletcher.  Practical Methods of Optimization , 1988 .

[18]  Kim-Hung Li,et al.  Imputation using Markov chains , 1988 .

[19]  I. Meilijson.  A fast improvement to the EM algorithm on its own terms , 1989 .

[20]  Adrian F. M. Smith,et al.  Sampling-Based Approaches to Calculating Marginal Densities , 1990 .