Location methods in experimental design

The design variables of an experiment is modeled as a facility location problem: we consider the case where the design variables are the coordinates of n points in a region of the plane and we look for the optimal configuration of the points under some constraints. In this paper we present a non-cooperative game theoretical model for the problem of experimental design: each of n virtual players decides the location of a point in the admissible region optimizing a pay-off function. The Nash equilibrium solutions will be the optimal solutions of the design variables problem. The resulting game has nice properties, so that a computational procedure is performed by using genetic algorithm approach and some existence results are obtained.