On the Utilization of Direct as Well as Collateral Information in the Problem of Statistical Estimation [Discussion]

Mr. Bailey's very interesting and important paper presents a novel departure from the conventional philosophies of statistical estimation. Although Mr. Bailey has concerned himself primarily with the derivation of estimation procedures through the application of Bayes' Theorem it. seems to me that he has made an even more basic contribution in his recognition of the fact that the parameters characterizing a group of related probability distributions may properly be considered as stochastic variables under certain conditions. As Mr. Bailey has pointed out this concept has heretofore been almost completely ignored by the recognized authorities in the field of mathematical statistics.