A data envelopment analysis method with assurance region for weight generation in the analytic hierarchy process

Data envelopment analysis (DEA) has been combined with the analytic hierarchy process (AHP) to form a DEAHP for weight derivation and aggregation in the AHP. This paper proposes a DEA model with assurance region (AR) for priority derivation in the AHP, which is referred to as the DEA/AR model. This new DEA model can overcome the shortcomings of the DEAHP such as illogical local weights, over insensitivity to some comparisons, information loss, and overestimation of some local weights, and provide better priority estimate and better decision conclusions than the DEAHP. Numerical examples including a real application of the AHP to the recruitment of a research fellow for a research project are provided to show the advantages of the DEA/AR model and its potential applications in multiple criteria decision analysis (MCDA).