"Causal Inference from Observational Data: How do we know we are RIGHT?" Jamie Robins, Harvard School of Public Health

QUANTITATIVE RESEARCH METHODS WORKSHOP

Abstract: Causal analyses of observational data are an exponential growth industry as are the methodologies to implement them. The questions I will address in this talk is how will we empirically determine which, if any, of the methods produce results that are sufficiently reliable to form part of the evidence base for some high stakes social and medical decisions ? Also., how will we learn to recognize those substantive studies for which valid estimation of causal effects is hopeless, regardless of analytic methodology? I will also address the ways in which the current sociology of science is itself an obstacle to our ability to answer.

James M. Robins is a Physician and the Mitchell L. and Robin LaFoley Dong Professor of Epidemiology and Professor of Biostatistics at the Harvard School of Public Health. The principal focus of Dr. Robins’ research has been the development of analytic methods appropriate for drawing causal inferences from complex observational and randomized studies with time-varying exposures or treatments. These methods are widely used in comparative effectiveness research, medicine, and epidemiology. They include inverse probability treatment weighted and doubly robust estimators of marginal structural models, the parametric g-formula estimator, and doubly robust g-estimation of structural nested models.

This virtual workshop is open to the Yale community. To receive Zoom information, please subscribe to the Quantitative Research Methods Workshop at this link: https://csap.yale.edu/quantitative-research-methods-workshop.

The series is sponsored by the ISPS Center for the Study of American Politics and The Whitney and Betty MacMillan Center for International and Area Studies at Yale with support from the Edward J. and Dorothy Clarke Kempf Fund. This workshop is being hosted jointly with the Leitner Political Economy Seminar