A model for efficiency evaluation based upon the theory of chance constrained programming is developed. The model uses a piecewise linear envelopment of confidence regions for observed stochastic multiple-input multiple-output combinations in the Data Envelopment Analysis (DEA) tradition. The model allows for an exogenous decomposition of the total variation in data for each Decision Making Unit (DMU). By varying certain probability levels the model can provide estimates of the sensitivity of efficiency scores regarding an unknown amount of noise in date. An application of the method in an evaluation of the research activities in economic departments at Danish Universities is presented.