Professor of Statistics and of Computer Science, Harvard University
My current primary interest concerns the development of experimental designs and statistical machine learning methods for informing sequential decision making in mobile health. These methods are used to construct real time treatment policies also known as Just-in-Time Adaptive Interventions (JITAIs). JITAIs are composed of a sequence of decision rules that specify in which user context it is most useful to provide an treatment as well as how to deliver the treatment to the user. The context is observed via sensor and self-report data and involves, for example, current and past user location, weather, social setting, user stress and mood, user behaviors and user engagement.