Activity Number:
|
190
- Contributed Poster Presentations: Section on Risk Analysis
|
Type:
|
Contributed
|
Date/Time:
|
Monday, July 30, 2018 : 10:30 AM to 12:20 PM
|
Sponsor:
|
Section on Risk Analysis
|
Abstract #329332
|
|
Title:
|
Parametric Likelihood Inference for Interval Censored and Left Truncated Competing Risks Data
|
Author(s):
|
Jung In Kim* and Jason P Fine and Margaret Gourlay and Byeongyeob Choi
|
Companies:
|
NIEHS and University of North Carolina at Chapel Hill and UNC-CH and University of Texas Health Science Center at San Antonio
|
Keywords:
|
Competing risks analysis;
Cumulative incidence function;
Interval censoring;
Left truncation
|
Abstract:
|
Hudgens et al. (2014) developed parametric modeling of the cumulative incidence function (CIF) for interval censored competing risks data. We extend their parametric models to account for both left truncation and interval censoring. A full likelihood estimator is still valid under a mixed case interval censoring model and an independent inspection process model. However, a naive likelihood method is shown to be invalid in both settings, while that without truncation is not valid only under an the independent inspection process model. This parametric method is applied to data from the study of osteoporotic fractures (SOF) to bone mineral density (BMD) testing interval with age as time scale.
|
Authors who are presenting talks have a * after their name.