Statistical Acceptance Sampling in a Competitive Environment

This paper presents a model and its solution for a statistical acceptance sample inventory problem in a competitive environment. The model is based upon the theory of games and is applied to a nuclear material accounting example. A game is formulated between a diverter who might deliberately steal valuable nuclear material and a defender who must make inferences based upon inventory difference. The diverter controls the mean of the inventory difference distribution which is not known by the defender. The solution presents a policy for the defender to estimate this distribution mean as well as other information to be used as the basis for additional statistical inferences.