The elimination of nuisance parameters has classically been tackled by various ad hoc devices, and has led to a number of attemps to define partial sufficiency and ancillarity. The Bayesian approach is clearly defined. This paper examines some classical procedures in order to see when they can be given a Bayesian justification.
Discussion on the papers by Mouchart, Michel and Simar, Léopold, Least squares approximation in Bayesian analysis and by Lindley, Dennis V., Approximate Bayesian methods, both of them part of a round table on Approximations held in the First International Congress on Bayesian Methods (Valencia, Spain, 28 May - 2 June 1979).
Discussion on the papers by DeGroot, Morris H., Improving predictive distributions and by Press, S. James, Bayesian inference in group judgement formulation and decision making using qualitative controlled feedback, both of them part of a round table on Improving judgements using feedback held in the First International Congress on Bayesian Methods (Valencia, Spain, 28 May - 2 June 1979).
Discussion on the paper by Barnard, George A., Pivotal inference and the Bayesian controversy, part of a round table on Bayesian and non-Bayesian conditional inference held in the First International Congress on Bayesian Methods (Valencia, Spain, 28 May - 2 June 1979).
Discussion on the papers by Makov, Udi E., Approximation of unsupervised Bayes learning procedures, Smith, Adrian F. M., Change-Point problems: approaches and applications and by Harrison, P. J. and Smith Jim Q., Discontinuity, decision and conflict, the three of them part of a round table on Sequential learning, discontinuities and changes held in the First International Congress on Bayesian Methods (Valencia, Spain, 28 May - 2 June 1979).
Discussion on the papers by Freeman, Peter R., On the number of outliers in data from a linear model and by Box, George E. P., Sampling inference, Bayes' inference and robustness in the advancement of learning, both of them part of a round table on Sensitivity to models held in the First International Congress on Bayesian Methods (Valencia, Spain, 28 May - 2 June 1979).
Page 1