Name in Chinese: 吴振科
The best way to contact me is email or mobile.
My main research interests include:
I conduct reasearch on the design and application of statistical methods that inform health decisions made by individuals, or precision medicine. My current focus is on latent variable and causal inference methods that can support disease etiology studies, medical diagnosis, and health policy evaluation. Broadly, the statistical goal is to discover simple latent structures that improve inferences and population parameters and individual latent states. I have also worked on causal inference methods 1) to evaluate novel treatment rules under special designs like matched-pair cluster randomized design, as these designs are useful for interventions that can only be applied at cluster level; and 2) to facilitate the inference for novel estimands in semiparametric models by automating and unifying the derivation of efficient influence functions (EIF) and ensuing estimation.
Currently a major focus of my work is on the analysis of multiple mixed-type longitudinal measurements with feedbacks in treatment assignments. I am working on hierarchical Bayesian methods to to infer latent trajectories that represent individual disease progressions that have direct applications to childhood pneumonia etiology studies and disease surveillance.
I am now teaching a PhD-level special topics course: BIOSTAT830 Statistical and Computational Methods for Learning Through Graphical Models, which will cover representation, inference, learning and causality demonstrated by case studies on real problems. Feel free to get what you need or comment on the course webpage.
I will join Department of Biostatistics at Univeristy of Michigan as Assistant Professor, with joint appointment at Michigan Institute for Data Science (MIDAS), starting from September 1st, 2016.
As part of their final project for Data Visualization for Individualized Health, Audrey Garman, Bengucan Gunen, Ruthe Huang, and Marcus Spearman, majored in public health studies, have built an excellent childhood pneumonia prediction visualization tool using Shiny. See the Hopkins inHealth and the HUB stories.
Theory and experiment, the pillars of 19-20th century science, have been joined by computation and big data in the 21st.
I am always looking for people who take a quantitative approach to studying public health, biology and biomedicine. Particular emphasis is placed on scalable Bayesian (graphical) modeling, latent variables, causal inference and especially their intersection. If you think you may be interested, please get in touch.
I’d be happy to answer questions on research and software!