Joseph B. Kadane

Joseph B. (Jay) Kadane

For me, statistics is an adventure in understanding how people make decisions and draw conclusions from data. Some of what I do to study this is theoretical, and some is applied. On the applied side, I find that I learn the most by choosing problems in very disparate fields. In the past, I've worked in econometrics, political science, archaeology, law, psychophysics, environment, medicine, and computer science, among others.

Currently, my applied projects include a study of how to prove age discrimination in court, using Markov Chain Monte Carlo methods to explore models in solid-state physics, and exploring various problems in statistical oceanography.

On the theoretical side, I am interested in Bayesian theory, both in its decision-theoretic foundations and in problems of elicitation (the process of determining probability distributions from background knowledge of investigators) and computation. When I do applied work, my commitment is to doing something useful in the applied context. But when my theoretical stance does not prove useful in some applied work, then I ponder that to try to understand why.

Some Related Publications

Kadane, J.B. and O'Hagan, A. (1995). "Using Finitely Additive Probability: Uniform Distributions on the Natural Numbers", Journal of the American Statistical Association, 90, 626--631.

Kadane, J.B. and Schum, D.A. (1996). "A Probabilistic Analysis of the Sacco and Vanzetti Evidence", J. Wiley & Sons.

"Bayesian Methods and Ethics in a Clinical Trial Design" (1996). J. B. Kadane, ed. John Wiley & Sons.

CMU HomeH&SS HomeStatistics