Simplified maximum likelihood inference based on the likelihood decomposition for missing data

Sangah Jung, Sangun Park

Research output: Contribution to journalArticle

Abstract

Summary: In this paper, we propose an estimation method when sample data are incomplete. We decompose the likelihood according to missing patterns and combine the estimators based on each likelihood weighting by the Fisher information ratio. This approach provides a simple way of estimating parameters, especially for non-monotone missing data. Numerical examples are presented to illustrate this method.

Original languageEnglish
Pages (from-to)271-283
Number of pages13
JournalAustralian and New Zealand Journal of Statistics
Volume55
Issue number3
DOIs
Publication statusPublished - 2013 Sep 1

Fingerprint

Likelihood Inference
Missing Data
Maximum Likelihood
Likelihood
Decompose
Fisher Information
Weighting
Estimator
Numerical Examples
Decomposition
Maximum likelihood
Inference
Missing data
Fisher information

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

@article{5169aa2d7b934079b94d8bd8e02af8c8,
title = "Simplified maximum likelihood inference based on the likelihood decomposition for missing data",
abstract = "Summary: In this paper, we propose an estimation method when sample data are incomplete. We decompose the likelihood according to missing patterns and combine the estimators based on each likelihood weighting by the Fisher information ratio. This approach provides a simple way of estimating parameters, especially for non-monotone missing data. Numerical examples are presented to illustrate this method.",
author = "Sangah Jung and Sangun Park",
year = "2013",
month = "9",
day = "1",
doi = "10.1111/anzs.12040",
language = "English",
volume = "55",
pages = "271--283",
journal = "Australian and New Zealand Journal of Statistics",
issn = "1369-1473",
publisher = "Wiley-Blackwell",
number = "3",

}

Simplified maximum likelihood inference based on the likelihood decomposition for missing data. / Jung, Sangah; Park, Sangun.

In: Australian and New Zealand Journal of Statistics, Vol. 55, No. 3, 01.09.2013, p. 271-283.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Simplified maximum likelihood inference based on the likelihood decomposition for missing data

AU - Jung, Sangah

AU - Park, Sangun

PY - 2013/9/1

Y1 - 2013/9/1

N2 - Summary: In this paper, we propose an estimation method when sample data are incomplete. We decompose the likelihood according to missing patterns and combine the estimators based on each likelihood weighting by the Fisher information ratio. This approach provides a simple way of estimating parameters, especially for non-monotone missing data. Numerical examples are presented to illustrate this method.

AB - Summary: In this paper, we propose an estimation method when sample data are incomplete. We decompose the likelihood according to missing patterns and combine the estimators based on each likelihood weighting by the Fisher information ratio. This approach provides a simple way of estimating parameters, especially for non-monotone missing data. Numerical examples are presented to illustrate this method.

UR - http://www.scopus.com/inward/record.url?scp=84886876101&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84886876101&partnerID=8YFLogxK

U2 - 10.1111/anzs.12040

DO - 10.1111/anzs.12040

M3 - Article

VL - 55

SP - 271

EP - 283

JO - Australian and New Zealand Journal of Statistics

JF - Australian and New Zealand Journal of Statistics

SN - 1369-1473

IS - 3

ER -