A new method based on data envelopment analysis for priority determination in the analytic hierarchy process

Recently Wang and Chin [A new data envelopment analysis method for priority determination and group decision making in the analytic hierarchy process, European journal of operational research, 2009: 195, 239-250] have proposed two LP models, based on DEA, for deriving the priority vectors from comparison matrices in the single and group AHP situations. Necessity of solving n LP models, normalizing the resulted local weights and using arithmetic mean to aggregate the comparison matrices of decision makers are the drawbacks of their models. In this paper we explain the drawbacks and present improved models that derive the normalized priority vector by solving just one LP and use geometric mean to aggregate the comparison matrices of decision makers.

Keywords:

Linear programming (LP) , Data envelopment analysis (DEA) , Analytic hierarchy process (AHP) , Group decision making