Entropy based Malmquist Productivity Index in Data Envelopment Analysis

Abstract

Malmquist Productivity Index (MPI) is one of the most famous indices, which is used for estimating the productivity change of a Decision Making Unit (DMU) during the time. Virtually any empirical study that uses MPI, reports average of the productivity indices they estimate to represent the overall tendency in productivity changes. In such a case, productivity indices of a DMU are considered with equal value. In this paper, we propose using the entropy of productivity indices of all DMUs at a specific part of time as the weight of indices of that in aggregating the indices during the under study time section. Then, we use the proposed method for an empirical study of 18 Iranian companies manufacturing automobiles and automobile parts, which have been accepted in Tehran Stock Exchange.