|
Activity Number:
|
487
|
|
Type:
|
Invited
|
|
Date/Time:
|
Thursday, August 10, 2006 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Committee on Women in Statistics
|
| Abstract - #305049 |
|
Title:
|
A Bayesian Hierarchical Model with Nest-Specific Covariates in Nest Survival Study
|
|
Author(s):
|
Jing Cao*+ and Chong He
|
|
Companies:
|
Southern Methodist University and Virginia Polytechnic Institute and State University
|
|
Address:
|
3225 Daniel Ave., Dallas, TX, 75275-0332,
|
|
Keywords:
|
Bayesian hierarchical model ; nest survival ; irregular visiting schedule ; intrinsic auto-regressive prior ; nest-specific covariates
|
|
Abstract:
|
Recently, logistic nest survival models have been developed to incorporate biological covariates with some restrictive assumptions. Also, the nest curve is assumed to be a parametric function (linear or quadratic) of nest age. We propose a Bayesian hierarchical model with nest-specific covariates to estimate age-specific daily survival rates. The model has the least restrictive assumptions, and it can handle irregular visiting schedules. The typical features of nest survival data---truncation and censoring---are accounted for by the likelihood function and latent variables. An intrinsic auto-regressive (IAR(2)) prior is employed for the nest age effect. This nonparametric prior provides a much more flexible and parsimonious alternative to the parametric specification. A simulation study and an analysis of a Missouri dickcissel dataset also are presented.
|
