Causal inference; observational data; biostatistics; survival analysis; Bayesian statistics

My goal is to ensure more patients can get reliable answers for their personal health questions. When a high quality trial to answer their questions is not available, or if the inclusion criteria were so strict that it is unclear whether the results apply to them, we turn to observational data. There is a wealth of information ready to be unlocked from observational data, but for many medically relevant settings the right causal inference methods to do so do not exist yet.

Drawing on my background in mathematics, I develop new causal inference methods, with the goal of increasing the number of (observational) data sets from which we can draw trustworthy causal conclusions. To facilitate the deployment of the new methods in practice, I publish free open source software (R packages).

My current research focus is on combining multiple data sets for causal inference, the regression discontinuity design, and high-dimensional causal inference.