Biostatistics doctoral student Xiangdong Gu to present at International Biometrics Society’s Spring Meeting

February 21, 2013

Biostatistics doctoral student Xiangdong Gu will present his paper “Study Design in the Presence of Error-prone Self-reported Outcomes” at the International Biometrics Society’s Eastern North American Region (ENAR) Spring 2013 meetings in Orlando, FL on March 10-13.

The paper is co-authored with Assistant Professor of Biostatistics Raji Balasubramanian, whose research expertise includes clinical trials and methods for the analysis of high dimensional mass spectrometry and systems biology data. Gu explains, “In the paper we consider studies in which data from sequentially administered, error-prone, laboratory-based diagnostic tests or self-reported questionnaires are collected to determine the occurrence of a silent event, whose occurrence is not known until we diagnose them, such as diabetes and cardiovascular diseases.”

Gu adds, “The problem is motivated by the Women's Health Initiative (WHI), in which information on diabetes status among the approximately 160,000 women is obtained from annually collected self-reported data. For this setting, using a likelihood-based approach we develop analytical solutions for power and sample size calculations and compare the relative efficiency of perfect versus imperfect diagnostic procedures. We also compare the relative efficiency of study designs under various missing data mechanisms and evaluate the effect of imperfect disease status ascertainment at baseline. Our method can help to compare different study designs and choose the most cost-effective one.”