In the past few years, efficient methods have been developed for bounding p
robabilities and expectations concerning univariate and multivariate random
variables based on the knowledge of some of their moments. Closed form as
well as algorithmic lower and upper bounds of this type are now available.
The lower and upper bounds are frequently close enough even if the number o
f utilized moments is relatively small. This paper shows how the probabilit
y bounds can be incorporated in probabilistic constrained stochastic progra
mming models in order to obtain approximate solutions for them in a relativ
ely simple way.