Speaker Details

Speaker 1

Peter Spirtes

Marianna Brown Dietrich Professor and Head of Philosophy at Carnegie Mellon University

Peter Spirtes Slides.pdf

Much of epidemiology, econometrics, sociology and political science is an attempt to infer causal relationships using data gathered under conditions where fully controlled experiments are not possible. The goals of my current research (called the TETRADproject) can be divided into two main parts. The first goal is to specify and prove under what conditions it is possible to reliably infer causal relationships from background knowledge and statistical data not obtained under fully controlled conditions. The second goal is to develop, analyze, implement, test and apply practical, provably correct computer programs for inferring causal structure under conditions where this is possible. The results of this research are available in the TETRAD II computer program. His research is interdisciplinary in nature, involving philosophy, statistics, graph theory and computer science. It has implications for the practices of a number of disciplines in which causal inferences from statistical data are made. The research that he has described shows that there are computer programs which can sometimes reliably draw useful causal conclusions under a reasonable set of assumptions. But there are still many cases where the assumptions he has made are known to be false. His current research centers on the extent to which these limiting assumptions can be relaxed, thereby extending the application of the results to a much wider class of phenomena and investigating the extent to which these search procedures can be made more reliable on small samples. This research program has important theoretical and practical implications. Theoretically, it will help us understand the relationship between probability and causality, and what the precise limits of reliable inference from uncontrolled data are. Practically, it will provide a useful tool for scientists that will help them build causal models. Spirtes joined Carnegie Mellon University's faculty in 1987. He earned a Ph.D. in history and philosophy of science and a Master of Science in computer science from the University of Pittsburgh.

Peter Spirtes's Webpage