The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.
Abstract Details
|
Activity Number:
|
306
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, August 2, 2011 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Biopharmaceutical Section
|
| Abstract - #300720 |
|
Title:
|
Application of the EM Algorithm for Mixtures of Distributions with Added Information
|
|
Author(s):
|
Chen Teel*+ and Taeyoung Park and Allan Sampson
|
|
Companies:
|
DuPont and Yonsei University and University of Pittsburgh
|
|
Address:
|
117 Presidential Drive, Greenville, DE, 19807,
|
|
Keywords:
|
EM algorithm ;
mixtures of distributions ;
conditional Bernoulli distribution ;
exponential family
|
|
Abstract:
|
The EM algorithm has been widely used to estimate parameters in mixtures of distributions where parameters in each component distribution are unknown and mixing proportions may be known or unknown. Here we consider such mixtures of distributions, but with added information as to mixture components. In particular, the mixtures of two exponential family distributions are considered when the number of observations within each mixture component is known. This situation frequently occurs in an adaptive design setting where block randomization are often used in clinical trials. By fully capitalizing on the additional information as to mixture component size, we develop a new computational method to implement the EM algorithm for mixtures of distribution. Our algorithm shows robustness to the choice of starting values and exhibits a fast and stable convergence property.
|
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 2011 program
|
2011 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.