Confidence interval estimation under the presence of non-Gaussian random errors: Applications to uncertainty analysis of chemical processes and simulation

Confidence intervals (CIs) are common methods to characterize the uncertain output of experimental measurements, process design calculations and simulations. Usually, probability distributions (pdfs) such as Gaussian and t-Student are used to quantify them. There are situationswhere the pdfs have anomalous behavior such as heavy tails, which can arise in uncertainty analysis of nonlinear computer models with vailable online 22 November 2009