|
Activity Number:
|
270
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, August 4, 2009 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Statistical Computing
|
| Abstract - #305328 |
|
Title:
|
Estimating Mixture Proportions When Categorized Data Are Available
|
|
Author(s):
|
Shiju Zhang*+
|
|
Companies:
|
St. Cloud State University
|
|
Address:
|
, , 56301,
|
|
Keywords:
|
Bernstein polynomial ; likelihood ; mixture density
|
|
Abstract:
|
The problem of estimating the mixture proportion of a two-component finite mixture distribution based on a sample from each component and a sample from the mixture is considered. Our method is likelihood-based. Since neither of the underlying component density is assumed known, the densities are first estimated with the categorized data using kernels or Bernstein polynomials. The mixture data likelihood then contains the only unknown proportion. The method is compared with existing methods through examples and numeric experiments.
|
- 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 2009 program |
