B.S. Wuhan University of Technology, 1982
M.S. Huazhong University of Science and Technology, 1987
Ph.D. Liverpool John Moores University, 2000
Bayesian Modeling and MCMC
Mixed Effects Models for Repeated Measurements
Joint Modeling for Longitudinal and Survival Data
Mixture of multilevel models for longitudinal data
Longitudinal Data Analysis
HIV/AIDS Clinical Research
Health Data Analysis
Bayesian methodology and Markov chain Monte Carlo
Joint models for longitudinal and survival data
Mixture of multilevel models for skewed-longitudinal data
Quantile regression for longitudinal and survival data
Parametric and nonparametric mixed effects models for skewed-longitudinal data
Missing data analysis and Measurement error modelling
HIV/AIDS dynamic modelling and prediction
Biostatistics to public health and medicine, in particular HIV/AIDS
Modelling ODE dynamic system for health research
Clinical research of infectious diseases and AIDS
Community-based data analysis
Dr. Huang's current research interests are (1) Development of various statistical models and associated Bayesian statistical methods to analyze longitudinal, repeated measurements, missing, censoring and survival data from epidemiological, medical and health fields, in particular, HIV/AIDS clinical studies. (2) Quantile regression for nonlinear or nonparametric mixed-effects joint models for longitudinal data with multiple features (3) A mixture of multilevel joint models with skew distributions for longitudinal and time-to-event data. (4) Joint models with skew distributions for longitudinal and survival data. Normality (symmetric) of the model random errors is a routine assumption for the mixed-effects models in many longitudinal studies, but it may be unrealistic obscuring important features of subject variations. Propose a class of models with considering model errors to be a skew distribution for joint behavior of longitudinal dynamic response process, an associated covariate process with measurement errors in conjunction with survival process. Bayesian parametric and nonparametric NLME modeling approaches are proposed to simultaneously estimate model parameters for statistical inference. (5) HIV dynamic modeling: Propose mathematical/statistical models-based a system of ordinary differential equations (ODE) for drug exposure (pharmacokinetics and adherence), drug susceptibility (resistance), drug efficacy and responses of antiretroviral therapies in clinical trials and health data; develop statistical inference methods including Bayesian sampling techniques (MCMC) to estimate parameters in ODE dynamic models.
Dr. Huang is a member of the American Statistical Association, International Chinese Statistical Association and the Royal Statistical Society. Dr. Huang served as the Associate Editor of Journal “Computational Statistics and Data Analysis” and the Guest Editor of “Journal of Probability and Statistics”. He is currently serving as Editorial Board in AIDS & Recent Advancements, Annals of Biometrics and Biostatistics and Austin Biometrics and Biostatistics.
USF Health: To envision and implement the future of health.