|
Activity Number:
|
442
- Disease Prediction, Statistical Methods for Genetic Epidemiology and Mis
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Thursday, August 12, 2021 : 4:00 PM to 5:50 PM
|
|
Sponsor:
|
Section on Statistics in Epidemiology
|
|
Abstract #318140
|
|
|
Title:
|
An Augmented Likelihood Approach for the Discrete Proportional Hazards Model and a Complex Survey Design, with Application to HCHS/SOL Study
|
|
Author(s):
|
Lillian Boe* and Pamela Shaw
|
|
Companies:
|
University of Pennsylvania and Kaiser Permanente Washington Health Research Institute
|
|
Keywords:
|
measurement error;
augmented likelihood;
misclassification;
surrogate endpoint;
proportional hazards
|
|
Abstract:
|
In certain epidemiologic settings, it is common to have infrequent follow-up for an expensive or otherwise burdensome gold standard outcome and more frequent follow-up for an error-prone or proxy outcome. Examples include a biopsy or intensive clinical exam that may be done infrequently and regular follow-up with a self-report instrument. We have developed a new augmented likelihood approach that incorporates error-prone, auxiliary outcomes into the analysis of gold standard time-to-event data in order to improve the efficiency of inference. This estimator is implemented for a complex survey design that includes both clustering and unequal probability sampling. We conduct a numerical study to show how we can improve statistical efficiency by using the proposed method instead of standard approaches for interval censored survival data that do not leverage the auxiliary data. We apply this method to data from the Hispanic Community Health Study/Study of Latinos in order to assess the association between energy and protein intake and the risk of incident diabetes mellitus when the dietary exposures of interest are also subject to measurement error.
|
Authors who are presenting talks have a * after their name.
