General Semiparametric AUC Regression Model with Discrete Covariates

• Activity Number: 42
• Type: Contributed
• Date/Time: Sunday, August 9, 2015 : 2:00 PM to 3:50 PM
• Sponsor: Biopharmaceutical Section
• Author(s): Yan Zhao* and Som Bohora and Taniana Balachova
• Companies: The University of Oklahoma Health Sciences Center and The University of Oklahoma Health Sciences Center and The University of Oklahoma Health Sciences Center
• Keywords: nonparametrics ; AUC ; Discrete Covariates ; Clinical trial

Abstract

In this article, we considered the analysis of data with a non-normally distributed response variable. In particular, we extended an existing AUC regression model that handles only two discrete covariates to a general AUC regression model that can be used on data with unrestricted number of discrete covariates. Comparing with other similar methods which require iterative algorithms and bootstrap procedure, our method involved only closed-form formulae for parameter estimation. The issue of model identifiability was also discussed. Our model has broad applicability in clinical trials due to the ease of interpretation on model parameters. We applied our method to analyze a clinical trial evaluating education materials for prevention of Fetal Alcohol Spectrum Disorders (FASDs). Finally, for a variety of simulation scenarios, our method produced parameter estimates with small biases and confidence intervals with nominal coverage probabilities.