|
Activity Number:
|
103
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Monday, August 4, 2008 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Nonparametric Statistics
|
| Abstract - #301262 |
|
Title:
|
L2 Estimation of Mixture Complexity
|
|
Author(s):
|
Umashanger Thayasivam*+ and T. N. Sriram+
|
|
Companies:
|
The University of Georgia and The University of Georgia
|
|
Address:
|
Department of statistics, Athens, GA, 30602-1952, Department of Statistics, Athens, GA, 30602,
|
|
Keywords:
|
Mixture Complexity ; Minimum Integrated Square distances ; robust estimation ; minimum distance
|
|
Abstract:
|
Developing statistical procedures to determine the number of components, known as mixture complexity, remains an area of intense research. In many applications, it is important to find the mixture with fewest components that provides a satisfactory fit to the data. Here, we focus on consistent estimation of unknown number of components in finite mixture models, when the exact form of the component densities are unknown but are postulated to be close to members of some parametric family. Minimum Integrated Square distances (L2E) are used to develop a robust estimator of mixture complexity, when all the parameters associated with the model are unknown. The estimator is shown to be consistent. We illustrate the use of our method for three well known datasets: the acidity data, enzyme data and galaxy 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 2008 program |
