Pivotal Methods in the Propagation of Distributions
Chih-Ming Wang, Jan Hannig, Hariharan K. Iyer
We propose a method for assigning a probability distribution to an input quantity. The distribution is used in the Monte Carlo method for uncertainty evaluation. The proposed method provides an alternative to other methods, such as the principle of maximum entropy and Bayesian procedure that were used in Supplement 1 to the Guide to the Expression of Uncertainty in Measurement for the same purpose. The method is based on an exact or approximate pivotal quantity and is easily applied. We use several examples from commonly known models to illustrate the implementation of the proposed approach.
Fiducial inference, GUM, Monte Carlo method, uncertainty