Point Decisions for Interval-Identified Parameters

This paper focuses on a situation where the decision-maker prefers to make a point-decision when the object of interest is interval-identified. Such a situation frequently arises when the interval-identified parameter is closely related to an optimal policy decision. To obtain a reasonable decision, this paper slices asymptotic normal experiments into subclasses corresponding to localized interval lengths, and finds a local asymptotic minimax decision for each subclass. Then, this paper suggests a decision that is based on the subclass minimax decisions, and explains the sense in which the decision is reasonable. One remarkable aspect of this solution is that the optimality of the solution remains intact even when the order of the interval bounds is misspecified. A small sample simulation study illustrates the solution’s usefulness.