De-biasing of calibration, obtained via prior assessment of parameters of distribution functions, provides a corrected probability distribution of further observation sets and hence, a more reliable means of estimating probabilities within a Bayesian framework. The paper explores the application of the technique to electrochemical processes, using membrane life-length, and the current efficiency of an electrolytic zinc-plating process as specific examples. (C) 2004 Elsevier B.V. All rights reserved.