Missing Region Modeling and the Multivariate Normal Mixture Model

• Nakamura Nagatomo

  Department of Economics, Sapporo Gakuin University

• Ueno Genta

  Department of Statistical Modeling, The Institute of Statistical Mathematics

• Higuchi Tomoyuki

  Department of Statistical Modeling, The Institute of Statistical Mathematics

• Konishi Sadanori

  Faculty of Mathematics, Kyushu University

Bibliographic Information

Other Title

• 欠損混合分布モデルとその応用
• ケッソン コンゴウ ブンプ モデル ト ソノ オウヨウ

Abstract

A dataset that contains missing regions is assumed to arise from two or more populations. In order to decompose the data into meaningful component distributions, a normal mixture model can be applied. A problem with this approach is that the estimated parameters are biased by fitting the standard normal mixture model. To correct the bias, a log-likelihood function for missing region probabilities is constructed, and the maximum likelihood estimators of the parameters - i.e. mix-ing proportions, mean vectors, and variance-covariance matrixes - are derived in the context of the EM algorithm. The performance of the model is verified by numerical experiments, and the model is applied to plasma velocity data.

Journal

• Ouyou toukeigaku

  Ouyou toukeigaku 34 (2), 57-73, 2005

  Japanese Society of Applied Statistics

Keywords

• extended-EM algorithm
• informative missing or non-ignorable data
• plasma velocity data

Details

• CRID: 1390282679419042176
• NII Article ID: 10017178501
• NII Book ID: AN00330942
• DOI: 10.5023/jappstat.34.57
• ISSN: 18838081
• ISSN: 02850370
• NDL BIB ID: 7969883
• Web Site: http://id.ndl.go.jp/bib/7969883
• Web Site: https://ndlsearch.ndl.go.jp/books/R000000004-I7969883
• Text Lang: ja
• Data Source:
  • JaLC
  • NDL
  • Crossref
  • CiNii Articles
  • KAKEN
• Abstract License Flag: Disallowed