Hongbin Zhang

Hongbin Zhang

Assistant Professor of Biostatistics

[email protected]

PhD, Statistics
University of British Columbia

MSc, Statistics
University of British Columbia

MS, Engineering and Computer Science
Chinese Academy of Sciences, Beijing, China

BSc, Mathematics
Peking University, Beijing, China

Dr. Zhang is a statistical methodologist and experienced biostatistician with skills in developing theory and computer algorithms for complex longitudinal data and with expertise in collaborative research. He is particularly interested in computationally intensive algorithms and computationally efficient alternatives. Examples of Dr. Zhang’s previous work include joint modelling of longitudinal data and survival outcomes. Dr. Zhang has shown that joint models that include a mechanistic nonlinear covariate model lead to much more accurate estimates compared to the standard joint model. Furthermore, Dr. Zhang has shown that when the survival outcome is modelled by accelerated failure time (AFT), even more insightful findings can be obtained. Findings from these investigations have been published in top tier statistical journals such as Statistics in Medicine, Annals of Applied Statistics and Journal of the Royal Statistical Society-Series C. Examples of biostatistical applications include studies in the field of HIV, orthopedic surgery, radiology, arthritis and others.

Dr. Zhang is a recipient of CUNY’s most competitive PSC-CUNY ENHC award, for a study on Neurocysticercosis cyst evolution using a multistate model, addressing data complexities such as latent pathway and loss-to-follow up. This study has led to several publications in medical journals and Statistics in Medicine, as well as an NIH R03 grant (dual-PI with Dr. Elizabeth Kelvin).

His implementation experience focuses on biostatistical applications and longitudinal studies with complex data and causal inference. As an example, jointly working with Dr. Denis Nash and researchers in Department of Health and Mental Hygiene, Dr. Zhang (as PI) recently obtained an NIH R21 grant to study the statistical methods to infer antiretroviral therapy initiation time (as random change-point model). He is also conducting HIV surveillance studies to evaluate WHO’s Treat-All policy using ‘target trial’ causal inference methods.