(Joyce) Chung-Chou H. Chang, PhD, Professor of Medicine, Biostatistics, and Clinical and Translational Science. Dr. Chang has a wide range of interests in theoretical and applied statistics, including time-to-event (survival) and longitudinal data analysis, missing data (competing risks and informative dropout), causal effect modeling (propensity score and marginal structural modeling), design and analysis of observational studies and clinical trials, design and analysis of studies of biomarkers in risk prediction, dynamic prediction, and machine learning techniques. As the lead statistician or consulting statistician, she has helped investigators throughout the University develop research protocols and data analysis plans for biomedical studies and has overseen the data management and analyses.
Dr. Chang encourages and promotes using the most up-to-date statistical methods. She has applied these methods to a range of investigations, including research on aging, HIV/AIDS and other infectious diseases, heart diseases, liver transplantation, health services research, and acute illness.
Education & Training
- MA (Mathematical Statistics), University of Pittsburgh, 1992
- PhD (Biostatistics), University of Pittsburgh, 1998
Chang CC, Zhao Y, Lee CW, Ganguli M. Smoking, death, and Alzheimer disease: a case of competing risks. Alzheimer Disease & Associated Disorders. 2012;26(4):300–306.
This study demonstrates that the effect of smoking on Alzheimer disease differs in models that are and are not adjusted for competing risks.
Bryce CL, Chang CCH, Ren Y, Yabes J, Zenarosa G, Iyer A, Tomko H, Squires RH, Roberts MS. Using time-varying models to estimate post-transplant survival in pediatric liver transplant recipients. PLOS One. 2018;13(5): e0198132.
Compared to Cox proportional hazards models, this study found that Gray’s piecewise constant time-varying coefficients models offered additional flexibility to identify additional covariates.
So-Armah K, Gupta SK, Kundu S, Stewart JC, Goulet JL, Butt AA, Sico JJ, Marconi VC, Crystal S, Rodriguez-Barradas MC, Budoff M, Gibert CL, Chang CC, Bedimo R, Freiberg MS. Depression and all-cause mortality risk in HIV-infected and HIV-uninfected US veterans: a cohort study. HIV Medicine. 2019;20(5):317-329.
Using Veterans Aging Cohort Study data, this study found that depression was associated with all-cause mortality. This association was modified by HIV status and method of depression ascertainment.
McDade E, Sun Z, Lee CW, Snitz B, Hughes T, Chang CC, Ganguli M. The association between pulse pressure change and cognition in late life: age and where you start matters. Alzheimer’s & Dementia: Diagnosis, Assessment & Disease Monitoring. 2016;4:56-66.
A prospective population-based cohort study suggested that the effect of pulse pressure on cognitive decline depends on age, baseline systolic blood pressure, and the trajectory of pulse pressure change.
- Survival and longitudinal data analysis
- Causal Effect Modeling
- Designs of Clinical Trials
- Risk Prediction