A modified Monte Carlo em algorithm for a three-parameter distribution

Z. Ye; M. Xie; Y. Shen; L. C. Tang

doi:10.1109/ICQR.2011.6031703

A modified Monte Carlo em algorithm for a three-parameter distribution

Z. Ye^*
, M. Xie
, Y. Shen
, L. C. Tang

^*Corresponding author for this work

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

Abstract

Statistical inference of a three-parameter distribution with closed-form mean residual life function is studied for complete and Type-II censored data. Because the log-likelihood function for this new distribution is not convex, the sequential quadratic programming method used for the maximum likelihood estimation easily diverges. Therefore, a modified Monte Carlo EM algorithm is proposed for parameter estimation. This modified algorithm is used to maintain the feasibility of the parameter vector during the evolutionary process, and is found to be robust in the sense that it is insensitive to the starting points. © 2011 IEEE.

Original language	English
Title of host publication	2011 IEEE International Conference on Quality and Reliability, ICQR 2011
Pages	172-176
DOIs	https://doi.org/10.1109/ICQR.2011.6031703
Publication status	Published - 2011
Externally published	Yes
Event	2011 IEEE International Conference on Quality and Reliability (ICQR 2011) - Bangkok, Thailand Duration: 14 Sept 2011 → 17 Sept 2011

Conference

Conference	2011 IEEE International Conference on Quality and Reliability (ICQR 2011)
Place	Thailand
City	Bangkok
Period	14/09/11 → 17/09/11

Research Keywords

Markov Chain Monte Carlo
Maximum likelihood estimation
Progressively Type-II censoring
Weibull distribution

Access Output

10.1109/ICQR.2011.6031703

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{2ebf5922e272430a8a6c1f53084c40fd,

title = "A modified Monte Carlo em algorithm for a three-parameter distribution",

abstract = "Statistical inference of a three-parameter distribution with closed-form mean residual life function is studied for complete and Type-II censored data. Because the log-likelihood function for this new distribution is not convex, the sequential quadratic programming method used for the maximum likelihood estimation easily diverges. Therefore, a modified Monte Carlo EM algorithm is proposed for parameter estimation. This modified algorithm is used to maintain the feasibility of the parameter vector during the evolutionary process, and is found to be robust in the sense that it is insensitive to the starting points. {\textcopyright} 2011 IEEE.",

keywords = "Markov Chain Monte Carlo, Maximum likelihood estimation, Progressively Type-II censoring, Weibull distribution",

author = "Z. Ye and M. Xie and Y. Shen and Tang, \{L. C.\}",

year = "2011",

doi = "10.1109/ICQR.2011.6031703",

language = "English",

isbn = "9781457706288",

pages = "172--176",

booktitle = "2011 IEEE International Conference on Quality and Reliability, ICQR 2011",

note = "2011 IEEE International Conference on Quality and Reliability (ICQR 2011) ; Conference date: 14-09-2011 Through 17-09-2011",

}

TY - GEN

T1 - A modified Monte Carlo em algorithm for a three-parameter distribution

AU - Ye, Z.

AU - Xie, M.

AU - Shen, Y.

AU - Tang, L. C.

PY - 2011

Y1 - 2011

N2 - Statistical inference of a three-parameter distribution with closed-form mean residual life function is studied for complete and Type-II censored data. Because the log-likelihood function for this new distribution is not convex, the sequential quadratic programming method used for the maximum likelihood estimation easily diverges. Therefore, a modified Monte Carlo EM algorithm is proposed for parameter estimation. This modified algorithm is used to maintain the feasibility of the parameter vector during the evolutionary process, and is found to be robust in the sense that it is insensitive to the starting points. © 2011 IEEE.

AB - Statistical inference of a three-parameter distribution with closed-form mean residual life function is studied for complete and Type-II censored data. Because the log-likelihood function for this new distribution is not convex, the sequential quadratic programming method used for the maximum likelihood estimation easily diverges. Therefore, a modified Monte Carlo EM algorithm is proposed for parameter estimation. This modified algorithm is used to maintain the feasibility of the parameter vector during the evolutionary process, and is found to be robust in the sense that it is insensitive to the starting points. © 2011 IEEE.

KW - Markov Chain Monte Carlo

KW - Maximum likelihood estimation

KW - Progressively Type-II censoring

KW - Weibull distribution

UR - https://www.scopus.com/pages/publications/80054728792

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-80054728792&origin=recordpage

U2 - 10.1109/ICQR.2011.6031703

DO - 10.1109/ICQR.2011.6031703

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 9781457706288

SP - 172

EP - 176

BT - 2011 IEEE International Conference on Quality and Reliability, ICQR 2011

T2 - 2011 IEEE International Conference on Quality and Reliability (ICQR 2011)

Y2 - 14 September 2011 through 17 September 2011

ER -

A modified Monte Carlo em algorithm for a three-parameter distribution

Abstract

Conference

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this