Aiyi Liu, Ph.D.

Senior Investigator

Biostatistics & Bioinformatics Branch


6710B 3230


Research Topics

Statistical Methods for Biomarkers in Diagnostics and Prediction

Biomarkers are often for diagnosis or prediction of disease. My research focuses on developing efficient statistical methods to evaluate the effectiveness of biomarkers in diagnosis and prediction.


I have been a member of the Biostatistics and Bioinformatics Branch since 2002. I received my doctorate degree from the University of Rochester in 1997. My research interests include: general statistical estimation theory, sequential methodology and adaptive designs with applications to clinical trials and other medical studies, linear models and regression analysis, analysis of repeated measurements and longitudinal data, multivariate data analysis and related topics, statistical methods for biomarkers including diagnostic biomarkers and ROC curve analysis, statistical methods for pooled assessments, and measurement errors.

Selected Publications

  1. Liu C, Liu A, Hu J, Yuan V, Halabi S. Adjusting for misclassification in a stratified biomarker clinical trial. Stat Med. 2014;33(18):3100-13.

  2. Liu A, Liu C, Zhang Z, Albert PS. Optimality of group testing in the presence of misclassification. Biometrika. 2012;99(1):245-251.

  3. Kang L, Liu A, Tian L. Linear combination methods to improve diagnostic/prognostic accuracy on future observations. Stat Methods Med Res. 2016;25(4):1359-80.

  4. Liu C, Liu A, Halabi S. A min-max combination of biomarkers to improve diagnostic accuracy. Stat Med. 2011;30(16):2005-14.

  5. Wu M, Shu Y, Li Z, Liu A. Repeated significance tests of linear combinations of sensitivity and specificity of a diagnostic biomarker. Stat Med. 2016;35(19):3397-412.

This page was last updated on July 26th, 2017