JSM 2012 Home

JSM 2012 Online Program

The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.

Online Program Home

Abstract Details

Activity Number: 642
Type: Topic Contributed
Date/Time: Thursday, August 2, 2012 : 10:30 AM to 12:20 PM
Sponsor: Section on Nonparametric Statistics
Abstract - #304698
Title: EM and Stochastic EM Algorithms for Reliability Mixture Models Under Random Censoring
Author(s): Didier Chauveau*+ and Laurent Bordes
Companies: UMR CNRS 7349 and UMR CNRS 4152
Address: CNRS MAPMO FDP, Orléans, _, 45067, France
Keywords: Censored data ; EM algorithm ; Finite mixture ; Semiparametric mixture ; Survival data
Abstract:

We present in this talk several iterative methods based on EM and Stochastic EM principles, that allow to estimate parametric or semiparametric reliability mixture models for randomly right censored lifetime data. We propose several possible levels of completion for the missing part of the data, coming from the underlying mixture and censoring process, resulting in different algorithms. For some parametric reliability mixture models, a genuine EM algorithm satisfying an ascent property for the observed likelihood is usable. When the M-step of this EM algorithm is not tractable, due to the parametric family considered or the level of complete data assumed, we show that Stochastic-EM algorithms provide efficient estimates. Some identifiable semiparametric mixture models are also proposed. In particular, we show that for semiparametric mixture with random censoring, a stochastic step is the only practical solution allowing computation of nonparametric estimates of the unknown survival function. The effectiveness of the new proposed algorithms is demonstrated through simulation study and estimates from actual data.


The address information is for the authors that have a + after their name.
Authors who are presenting talks have a * after their name.

Back to the full JSM 2012 program




2012 JSM Online Program Home

For information, contact jsm@amstat.org or phone (888) 231-3473.

If you have questions about the Continuing Education program, please contact the Education Department.