Caucasian

FIND A PRESENTER

speaker-image

James Robins

Epidemiologist and Biostatistician best known for advancing methods for drawing causal inferences from complex observational studies

James M. Robins is an M.D. and the Mitchell L. & Robin  LaFoley Dong Professor of Epidemiology and Professor of Biostatistics at the Harvard T. H. Chan School of Public Health. He is best known for the development of analytic methods appropriate for drawing causal inferences from complex observational and randomized studies with time-varying exposures…

Categories :

Full Bio

James M. Robins is an M.D. and the Mitchell L. & Robin  LaFoley Dong Professor of Epidemiology and Professor of Biostatistics at the Harvard T. H. Chan School of Public Health. He is best known for the development of analytic methods appropriate for drawing causal inferences from complex observational and randomized studies with time-varying exposures or treatments.  He is the developer of the so-called ‘G Methods’. These methods include the estimated G –formula, inverse probability of treatment weighted and doubly robust estimators of static and dynamic marginal structural models, and doubly robust G-estimation of structural nested failure time and mean models. These methods are now in wide use, particularly in medical research. The usual approach to the estimation of the effect of a time-varying treatment or exposure on time to disease is to model the hazard incidence of failure at time t as a function of past treatment history using a time-dependent Cox proportional hazards model. Dr. Robins has shown the usual approach may be biased whether or not further adjusts for past confounder history in the analysis. Dr. Robins has applied his methods to analyze the effect of a non-randomized treatment aerosolized pentamidine on the survival of AIDS patients in ACTG Trial 002; the effect of arsenic exposure on the mortality experience of a cohort of Montana copper smelter workers; the effect of formaldehyde on the respiratory disease mortality of a cohort of U.S. chemical workers; and the effect of smoking cessation on subsequent myocardial infarction and death within the MRFIT randomized trial.

Check Availability

Check Availability for

Topics

Causal inference, machine learning, and optimal decisions
The optimal treatment, e.g. the best drug to prescribe, or action , e.g. the best online add to present to a consumer, depend on the past medical or purchasing history of patients and consumers. In his talk, he will discuss how to use high dimensional data to estimate the optimal treatment or action for a given individual based on data collected on their past history either from observational, non-experimental data, or from a combination of randomized assignment (AB testing ) data and non-experimental data. He will describe why these causal methods are needed and, through case studies, show how much better they perform in practice compared to purely association machine learning methods.

Videos

April 24, 2019 Seminar Series: James Robins

Books

Please Contact Us For More Information

News

Please Contact Us For More Information

Testimonials

Please Contact Us For More Information

GET IDEAS

form-arrow

1 HOUR OR LESS