Online Program Home
My Program

Abstract Details

Activity Number: 609 - New Approaches to Improving Accuracy, Precision, and Robustness of Survival Analysis
Type: Contributed
Date/Time: Thursday, August 1, 2019 : 8:30 AM to 10:20 AM
Sponsor: Biometrics Section
Abstract #300632
Title: On Objective Biomarker Development for Regression Calibration
Author(s): Cheng Zheng* and Yiwen Zhang and Ying Huang and Ross L. Prentice
Companies: University of Wisconsin at Milwakee and University of Wisconsin-Milwaukee and Fred Hutchinson Cancer Research Center and Fred Hutchinson Cancer Research Center
Keywords: Measurement Error; Regression Calibration; Feeding Study; Biomarker; Cardiovascular Diseases; Survival Analysis

It is important to correct the systematic measurement error in self-reported data when studying the associations between dietary intakes and risks of diseases. Regression calibration method was established when an objectively measured biomarker that satisfies the classical measurement error assumption is available. However, very few biomarkers as such have been developed. Recent feeding studies provided great opportunities to develop potential biomarkers from traditional regression methods for a much larger variety of dietary components. However the measurement error for these biomarkers will be Berkson type and thus are not applicable to the existing regression calibration method. We show that ignoring the violation of the classical measurement error assumption lead to biased association estimation; and we propose three ways to obtain consistent estimations. The asymptotics of these estimators are derived. Theoretical and numerical analyses were performed to compare these estimators and we applied them to the women's health initiative (WHI) study to re-examine the associations between sodium/potassium intake ratio and cardiovascular diseases.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2019 program