Stochastic EM

Research output: Chapter in Book/Report/Conference proceedingEncyclopedia chapterResearch

Abstract

The expectation maximization (EM) algorithm is a useful tool for finding the maximum likelihood estimator (MLE) in incomplete data problems. In some problems, however, the E step (and/or the M step) of the algorithm may be difficult to implement. Here, the stochastic EM algorithm can provide a useful alternative by replacing the E step of the EM algorithm with a fixed number of simulations, turning the M step into a maximization of the complete data log‐likelihood. The output of the stochastic EM algorithm forms a Markov chain that under sufficient regularity conditions is ergodic with an asymptotically normal invariant distribution. Draws from the invariant distribution form a consistent asymptotically normal estimator of the unknown parameters.
Original languageEnglish
Title of host publicationWiley StatsRef : Statistics Reference Online
EditorsMarie Davidian, Ron S. Kenett, Nicholas T. Longford, Geert Molenberghs, Walter Piegorsch, Fabrizio Ruggeri
Place of PublicationHoboken, NJ
PublisherWiley
Publication date15 May 2018
ISBN (Electronic)9781118445112
DOIs
Publication statusPublished - 15 May 2018

Bibliographical note

CBS Library does not have access to the material

Keywords

  • Incomplete data
  • EM algorithm
  • Imputation
  • Simulation
  • Estimation

Cite this

Nielsen, S. F. (2018). Stochastic EM. In M. Davidian, R. S. Kenett, N. T. Longford, G. Molenberghs, W. Piegorsch, & F. Ruggeri (Eds.), Wiley StatsRef: Statistics Reference Online Hoboken, NJ: Wiley. https://doi.org/10.1002/9781118445112.stat08121
Nielsen, Søren Feodor. / Stochastic EM. Wiley StatsRef: Statistics Reference Online. editor / Marie Davidian ; Ron S. Kenett ; Nicholas T. Longford ; Geert Molenberghs ; Walter Piegorsch ; Fabrizio Ruggeri. Hoboken, NJ : Wiley, 2018.
@inbook{e64d95c0f1a84c4183c589a21c54fbae,
title = "Stochastic EM",
abstract = "The expectation maximization (EM) algorithm is a useful tool for finding the maximum likelihood estimator (MLE) in incomplete data problems. In some problems, however, the E step (and/or the M step) of the algorithm may be difficult to implement. Here, the stochastic EM algorithm can provide a useful alternative by replacing the E step of the EM algorithm with a fixed number of simulations, turning the M step into a maximization of the complete data log‐likelihood. The output of the stochastic EM algorithm forms a Markov chain that under sufficient regularity conditions is ergodic with an asymptotically normal invariant distribution. Draws from the invariant distribution form a consistent asymptotically normal estimator of the unknown parameters.",
keywords = "Incomplete data, EM algorithm, Imputation, Simulation, Estimation, Incomplete data, EM algorithm, Imputation, Simulation, Estimation",
author = "Nielsen, {S{\o}ren Feodor}",
note = "CBS Library does not have access to the material",
year = "2018",
month = "5",
day = "15",
doi = "10.1002/9781118445112.stat08121",
language = "English",
editor = "Marie Davidian and Kenett, {Ron S.} and Longford, {Nicholas T.} and Geert Molenberghs and Walter Piegorsch and Fabrizio Ruggeri",
booktitle = "Wiley StatsRef",
publisher = "Wiley",

}

Nielsen, SF 2018, Stochastic EM. in M Davidian, RS Kenett, NT Longford, G Molenberghs, W Piegorsch & F Ruggeri (eds), Wiley StatsRef: Statistics Reference Online. Wiley, Hoboken, NJ. https://doi.org/10.1002/9781118445112.stat08121

Stochastic EM. / Nielsen, Søren Feodor.

Wiley StatsRef: Statistics Reference Online. ed. / Marie Davidian; Ron S. Kenett; Nicholas T. Longford; Geert Molenberghs; Walter Piegorsch; Fabrizio Ruggeri. Hoboken, NJ : Wiley, 2018.

Research output: Chapter in Book/Report/Conference proceedingEncyclopedia chapterResearch

TY - ENCYC

T1 - Stochastic EM

AU - Nielsen, Søren Feodor

N1 - CBS Library does not have access to the material

PY - 2018/5/15

Y1 - 2018/5/15

N2 - The expectation maximization (EM) algorithm is a useful tool for finding the maximum likelihood estimator (MLE) in incomplete data problems. In some problems, however, the E step (and/or the M step) of the algorithm may be difficult to implement. Here, the stochastic EM algorithm can provide a useful alternative by replacing the E step of the EM algorithm with a fixed number of simulations, turning the M step into a maximization of the complete data log‐likelihood. The output of the stochastic EM algorithm forms a Markov chain that under sufficient regularity conditions is ergodic with an asymptotically normal invariant distribution. Draws from the invariant distribution form a consistent asymptotically normal estimator of the unknown parameters.

AB - The expectation maximization (EM) algorithm is a useful tool for finding the maximum likelihood estimator (MLE) in incomplete data problems. In some problems, however, the E step (and/or the M step) of the algorithm may be difficult to implement. Here, the stochastic EM algorithm can provide a useful alternative by replacing the E step of the EM algorithm with a fixed number of simulations, turning the M step into a maximization of the complete data log‐likelihood. The output of the stochastic EM algorithm forms a Markov chain that under sufficient regularity conditions is ergodic with an asymptotically normal invariant distribution. Draws from the invariant distribution form a consistent asymptotically normal estimator of the unknown parameters.

KW - Incomplete data

KW - EM algorithm

KW - Imputation

KW - Simulation

KW - Estimation

KW - Incomplete data

KW - EM algorithm

KW - Imputation

KW - Simulation

KW - Estimation

U2 - 10.1002/9781118445112.stat08121

DO - 10.1002/9781118445112.stat08121

M3 - Encyclopedia chapter

BT - Wiley StatsRef

A2 - Davidian, Marie

A2 - Kenett, Ron S.

A2 - Longford, Nicholas T.

A2 - Molenberghs, Geert

A2 - Piegorsch, Walter

A2 - Ruggeri, Fabrizio

PB - Wiley

CY - Hoboken, NJ

ER -

Nielsen SF. Stochastic EM. In Davidian M, Kenett RS, Longford NT, Molenberghs G, Piegorsch W, Ruggeri F, editors, Wiley StatsRef: Statistics Reference Online. Hoboken, NJ: Wiley. 2018 https://doi.org/10.1002/9781118445112.stat08121