Asymptotic properties of the EM algorithm estimate for normal mixture models with component specific variances
Most of the researchers in the application areas usually use the EM algorithm to find estimators of the normal mixture distribution with unknown component specific variances without knowing much about the properties of the estimators. It is unclear for which situations the EM algorithm providesgoode...
Saved in:
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Article |
Published: |
2018
|
Subjects: | |
Online Access: | https://repository.li.mahidol.ac.th/handle/123456789/20834 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Mahidol University |
id |
th-mahidol.20834 |
---|---|
record_format |
dspace |
spelling |
th-mahidol.208342018-07-24T10:27:38Z Asymptotic properties of the EM algorithm estimate for normal mixture models with component specific variances Dechavudh Nityasuddhi Dankmar Böhning Mahidol University Freie Universitat Berlin Computer Science Mathematics Most of the researchers in the application areas usually use the EM algorithm to find estimators of the normal mixture distribution with unknown component specific variances without knowing much about the properties of the estimators. It is unclear for which situations the EM algorithm providesgoodestimators, good in the sense of statistical properties like consistency, bias, or mean square error. A simulation study is designed to investigate this problem. The scope of this study is set for the mixture model of normal distributions with component specific variance, while the number of components is fixed. The asymptotic properties of the EM algorithm estimate is investigated in each situation. The results show that the EM algorithm estimate does provide good asymptotic properties except for some situations in which the population means are quite close to each other and larger differences in the variances of the component distributions occur. © 2002 Elsevier Science B.V. All rights reserved. 2018-07-24T03:23:15Z 2018-07-24T03:23:15Z 2003-01-28 Article Computational Statistics and Data Analysis. Vol.41, No.3-4 (2003), 591-601 10.1016/S0167-9473(02)00176-7 01679473 2-s2.0-0037469119 https://repository.li.mahidol.ac.th/handle/123456789/20834 Mahidol University SCOPUS https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=0037469119&origin=inward |
institution |
Mahidol University |
building |
Mahidol University Library |
continent |
Asia |
country |
Thailand Thailand |
content_provider |
Mahidol University Library |
collection |
Mahidol University Institutional Repository |
topic |
Computer Science Mathematics |
spellingShingle |
Computer Science Mathematics Dechavudh Nityasuddhi Dankmar Böhning Asymptotic properties of the EM algorithm estimate for normal mixture models with component specific variances |
description |
Most of the researchers in the application areas usually use the EM algorithm to find estimators of the normal mixture distribution with unknown component specific variances without knowing much about the properties of the estimators. It is unclear for which situations the EM algorithm providesgoodestimators, good in the sense of statistical properties like consistency, bias, or mean square error. A simulation study is designed to investigate this problem. The scope of this study is set for the mixture model of normal distributions with component specific variance, while the number of components is fixed. The asymptotic properties of the EM algorithm estimate is investigated in each situation. The results show that the EM algorithm estimate does provide good asymptotic properties except for some situations in which the population means are quite close to each other and larger differences in the variances of the component distributions occur. © 2002 Elsevier Science B.V. All rights reserved. |
author2 |
Mahidol University |
author_facet |
Mahidol University Dechavudh Nityasuddhi Dankmar Böhning |
format |
Article |
author |
Dechavudh Nityasuddhi Dankmar Böhning |
author_sort |
Dechavudh Nityasuddhi |
title |
Asymptotic properties of the EM algorithm estimate for normal mixture models with component specific variances |
title_short |
Asymptotic properties of the EM algorithm estimate for normal mixture models with component specific variances |
title_full |
Asymptotic properties of the EM algorithm estimate for normal mixture models with component specific variances |
title_fullStr |
Asymptotic properties of the EM algorithm estimate for normal mixture models with component specific variances |
title_full_unstemmed |
Asymptotic properties of the EM algorithm estimate for normal mixture models with component specific variances |
title_sort |
asymptotic properties of the em algorithm estimate for normal mixture models with component specific variances |
publishDate |
2018 |
url |
https://repository.li.mahidol.ac.th/handle/123456789/20834 |
_version_ |
1763494944970899456 |