ON THE TREATMENT OF CORRELATED NORMAL AND LOGNORMAL INPUT VARIABLES IN UNCERTAINTY PROPAGATION

It has been pointed out that correlations among input variables can cause considerable underestimation in uncertainty propagation in probabilistic safety assessment. Reference 1 developed a method to solve this problem based on the assumption that all input variables are either normally or lognormally distributed and the perfectly correlated variables are affected by a common uncertainty source in the same direction. This paper presents the formula to deal with the case where some input variables are normally distributed while the others are lognormally distributed and the directions can be either the same or opposite.