Using kullback-leibler distance for performance evaluation of search designs

Abstract

This paper considers the search problem, introduced by Srivastava [10]. This is a model discrimination problem. In the context of search linear models, discrimination ability of search de- signs has been studied by several researchers. Some criteria have been developed to measure this capability, however, they are re- stricted in a sense of being able to work for searching only one possible nonzero effect. In this paper, two criteria are proposed, based on Kullback-Leibler distance. These criteria are able to eval- uate the search ability of designs, without any restriction on the number of nonzero effects. © 2011 Iranian Mathematical Society.