Abstract
Differences between inferences obtained from Bayesian reliability models using system-level data versus component-level data have recently motivated a call for a "basic restructuring of the Bayes procedure [1]." In this note, I explore the source of such differences and demonstrate that Bayesian models would be aberrant only if such differences did not exist.
Disciplines
Statistical Methodology | Statistical Theory
Suggested Citation
Johnson, Valen E., "Bayesian Aggregation Error?" (February 2006). UT MD Anderson Cancer Center Department of Biostatistics Working Paper Series. Working Paper 11.
http://biostats.bepress.com/mdandersonbiostat/paper11