My methodological research is motivated by collaborations with the Penn Statistics in Imaging and Visualization Endeavor (PennSIVE), Oathes lab at Penn, Leonard Davis Institute (LDI), Center for Health Incentives and Behavioral Economics (CHIBE), Penn Implementation Science Center (PISCE), and Penn Nudge Unit. Main themes of my research include the design and analysis of clinical trials, personalized medicine, and the analysis of neuroimaging data. Within those broad categories, I am most excited about ongoing work related to Sequential Multiple Assignment Randomized Trials (SMART) and cluster randomized trials, dynamic treatment regimes, and personalizing the application of transcranial magnetic stimulation for treating depression.
During my post-doctoral fellowship, I worked on fusing ideas from causal inference with machine learning to reduce the effects of confounding and selection bias on neurological disease patterns estimated from structural magnetic resonance imaging.
Some of the images below link to more detailed descriptions of work I led during my post-doctoral and PhD training. I'm in the process of adding descriptions of more recent research projects, so please check back soon for updates.
SVM feature standardization for multivariate pattern analysis
Addressing confounding in multivariate pattern analysis
Data fusion techniques for multimodal neuroimaging studies
Optimal dynamic treatment regimes for probabilities and quantiles