We examine and extend the formal duality of data fusion with response management. This builds on the well-known estimation/control duality and the duality discovered by Bowman between data association and planning. We extend this duality to the partitioning of classes of applications and, specifically to classes of state variables to be estimated or controlled. Management can involve any degree of influence, just as fusion can involve any degree of information quality. “Managed” entities can differ enormously in their controllability and therefore in the degree to which they can be considered to be “resources.” This is why we use the term response management rather than resource management in this paper's title: resource is often a fuzzy concept. The fusion/management duality extends beyond functionality to encompass processing architectures, classes of outputs, and inference methods.