|
Activity Number:
|
119
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Monday, August 7, 2006 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Nonparametric Statistics
|
| Abstract - #305769 |
|
Title:
|
Prevalence Estimation from Multiple Incomplete Lists Using the Rasch Model
|
|
Author(s):
|
Changxuan Mao*+
|
|
Companies:
|
University of California, Riverside
|
|
Address:
|
Department of Statistics, Riverside, CA, 92507,
|
|
Keywords:
|
capture-recapture ; Rasch model ; mixture model ; conditional likelihood ; population size ; species richness
|
|
Abstract:
|
In epidemiological studies, a target population of individuals with disease might appear in multiple registration lists. However, these lists may be incomplete. Estimating the total population size from such incomplete list data is important to both scientific research and management. A Rasch model can be used to model these presence indicators, in which the logit of the presence probability is decomposed into individual catchability and list effect. A nonparametric Rasch model is considered. A family of lower bounds to the population size is proposed.
|
