|
Activity Number:
|
231
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, August 5, 2008 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Statistics in Epidemiology
|
| Abstract - #300575 |
|
Title:
|
Identifiability of Bivariate Mixtures: An Application to Infant Mortality Models
|
|
Author(s):
|
Eric Y. Frimpong*+ and Timothy B. Gage and Howard Stratton
|
|
Companies:
|
University at Albany and University at Albany and University at Albany
|
|
Address:
|
Arts & Sciences Building, Room 237 , Albany, NY, 12222,
|
|
Keywords:
|
Mixture models ; Latent subgroups ; Identifiability ; infant mortality ; birth weight
|
|
Abstract:
|
Identifiability of the parameters for a Mixture of Bivariate Densities (MBD) in the form $f(x,y;\beta,\theta,\pi)=\pi f(y|x;\beta_1)f(x;\theta_1)+(1-\pi)f(y|x;\beta_2)f(x;\theta_2)$ is considered. Particular attention is given to $\theta_1\ne\theta_2$ (i.e. marginal of $x$ is a nondegenerate mixture). Characterizations of identifiability that includes extensions of Hennig (2000), Hunter (2007) and Gage (2004) models are given. These identified models are applied to characterize latent subpopulations related to infant mortality and survival in several NCHS linked Birth/Death data sets.
|
