Forty years ago, the following disciplines had their own languages, opinions and idiosyncrasies re causal inference: philosophy, computer science, sociology, psychology, statistics, epidemiology, political science, and economics. Today all speak a common language. Top journals have gone from knee-jerk rejection to active solicitation of articles on causal inference. The ongoing rapid development of the field has been driven by:
End of the historical suppression of causal language in statistics and medicine (aside from randomized clinical trials);
The internet making cross disciplinary understanding and collaboration easy;
The need for individualized treatment regimes in Medicine;
Tech companies realizing that optimizing profits depended on causal interventions rather than just prediction;
The development of causal graphs that offers non-technical users the ability to validly reason about complex causal systems;
The existence of huge data sets leading to data driven science rather than hypothesis driven science.
In my lecture, I will give a history of statistical methods for causal inference, focusing on methods developed by myself and colleagues. I will explain why causal methods have had such a large impact in substantive areas in which confounding by time varying covariates is very strong, as in studies of HIV-infected individuals. These causal methods are also an integral part of the target trial methodology - a methodology that is altering the analytical paradigm for the estimation of causal effects from longitudinal observational data in Medicine and Public Health. I will conclude with a discussion of the future of causal inference in the coming age of AI.
What is a Rothschild Distinguished Visiting Fellow? The fellowship allows pre-eminent mathematicians from around the world to join a programme, where they deliver keynote seminars at the Institute and give lectures across the UK.