Abstract
This paper deals with stochastic goal programming as a method capable of providing “satisficing” solutions in the uncertainty case from the standard expected utility perspective. By extending recent results on ARA-based weighted achievement function and goal structures leading to mean-variance optimization, the paper combines random with non-random goals, and explains the role of ARA coefficients in the model. Eight applications to real world problems in managerial environments are described. A case study in the textile industry, the choice of fibers to make blends in yam production, is developed from empirical information and numerically solved.