2019 Fisher Lecturer Winner
The 2019 Committee of Presidents of Statistical Societies (COPSS) Fisher Lectureship Committee selected Paul R. Rosenbaum, Wharton School of the University of Pennsylvania to deliver the Fisher Lecture at the Joint Statistical Meetings in 2019. The citation for Dr. Rosenbaum's plaque reads:
“For pioneering contributions to statistical methodology for observational studies, important applications of such methodology to health outcomes studies, lucid books on statistical principles and methodology for observational studies and excellent mentoring."
Dr. Rosenbaum's talk is titled “An Observational Study Used to Illustrate Methodology for Such Studies". The lecture can be viewed online.
A natural experiment in health outcomes research is used to frame a discussion of statistical methods for causal inference in observational studies. A narrative description of the study’s design, analysis and reception is interrupted twice, first to describe algorithmic developments in optimal matching in design, second to describe analyses that inform discussions of unobserved biases due to the absence of randomized treatment assignment. Specific topics include: (i) fine balance constraints imposed on minimum distance matched samples, (ii) sensitivity analyses when treatment effects are heterogeneous, and (iii) design sensitivity as a tool to evaluate study designs and analytical techniques.