Abstract Details
Activity Number:
|
680
|
Type:
|
Topic Contributed
|
Date/Time:
|
Thursday, August 8, 2013 : 10:30 AM to 12:20 PM
|
Sponsor:
|
Section on Statistics in Epidemiology
|
Abstract - #309680 |
Title:
|
Assessing the Association Between Time-to-Pregnancy and Woman-Specific Menstrual Cycle Length Mean and Variability Using a Bayesian Hierarchical Model
|
Author(s):
|
Kirsten Lum*+ and Germaine M. Buck Louis and Thomas A. Louis and Rajeshwari Sundaram
|
Companies:
|
Johns Hopkins Bloomberg School of Public Health and National Institute of Child Health and Human Development and Johns Hopkins Bloomberg School of Public Health and National Institute of Child Health and Human Development
|
Keywords:
|
Bayesian hierarchical model ;
joint model ;
longitudinal ;
menstrual cycle ;
time-to-pregnancy ;
variability
|
Abstract:
|
There is considerable interest in the impact of the variability of longitudinal risk factors on time-to-event health outcomes. A motivating example of this from prospective pregnancy studies is the role that menstrual cycle length variability may play in time-to-pregnancy (TTP). We propose a joint model composed of a Bayesian hierarchical model for longitudinal menstrual cycle length, with a flexible parametric distribution that allows for skewness, and a grouped transformation model for TTP. In the longitudinal model, we use a fully Bayesian approach to estimate the posterior distribution of unobserved features of a woman's underlying distribution of cycle lengths (e.g. mean, variance, IQR, etc.), as a function of longitudinally observed cycle lengths and prior parameters, weighted by the number of cycles. We use Markov chain Monte Carlo to obtain the unconditional survivor and hazard functions for estimation of TTP parameters. We compare mixing over the full posterior distribution versus using a point estimate of the mean of the posterior; and we illustrate our approach with data from the Longitudinal Investigation of Fertility and the Environment Study.
|
Authors who are presenting talks have a * after their name.
Back to the full JSM 2013 program
|
2013 JSM Online Program Home
For information, contact jsm@amstat.org or phone (888) 231-3473.
If you have questions about the Continuing Education program, please contact the Education Department.
The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.
Copyright © American Statistical Association.