ABSTRACT
Probabilistic methods are normally used to evaluate statistical distribution of a performance function Y = g(X1,X2,…,Xn) based on known statistical features of input variables Xi. Due to its complexity, the probabilistic methods can be classified into three categories: methods which do not consider spatial randomness of input variables, methods which consider spatial variability of input variables and hybrid methods. Methods which neglect spatial variability are commonly used in stability analysis. The most popular are the Monte Carlo method (MCM), the First Order Second Moment method (FOSM) and the Point Estimate method (PEM).
