Applying Non-parametric Robust Bayesian Analysis to Non-opiniated Judicial Neutrality

This paper explores the usefulness of robust Bayesian analysis in the context of an applied problem, 6nding priors to model judicial neutrality in an age discrimination case. We seek large classes of prior distributions without trivial bounds on the posterior probability of a key set, that is, without bounds that are independent of the data. Such an exploration shows qualitatively where the prior elicitation matters most, and quantitatively how sensitive the conclusions are to speci6ed prior changes. The novel non-parametric classes proposed and studied here represent judicial neutrality and are reasonably wide, so that when a clear conclusion emerges from the data at hand, this is arguably very reliable. c © 2002 Published by Elsevier Science B.V.