Tianchen Qian

Research. 

        The theme of our research group is developing data science tools for optimizing adaptive digital interventions. We contribute new methodology and software for

• causal inference — such as how to define and estimate causal effects in longitudinal settings with time-varying treatments;

• experimental design — such as how to design micro-randomized trials for mHealth interventions;

• policy learning — such as how to learn the optimal way of delivering interventions from offline or online data.

        We collaborate with scientists on digital intervention development from a variety of domains, including physical activity, substance abuse, smoking cessation, weight management, drinking behavior, anger management, and so on.

        We also have work in the following areas:

• semiparametric efficiency theory;

• clinical trial design and analysis;

• Alzheimer's disease and related dementia.

        Here are selected publications by topic, with more context on each of the directions.

Training and Education.

• 2017-2020: postdoc, Department of Statistics, Harvard University, mentored by Susan Murphy

• 2012-2017: Ph.D. in Biostatistics, Johns Hopkins University, advised by Constantine Frangakis and Michael Rosenblum

• 2008-2012: B.S. in Mathematics, Tsinghua University