Article Preview
Top1. Introduction
In practice, production engineers regularly assess efficiency and productivity of manufacturing processes to achieve business goals (Park et al., 2018. Typically, measurement of a production unit-performance is crucial in determining whether it has achieved its objectives or not, and it generates a phase of management process that consists of feedback motivation phases (Kumar and Gulati, 2008; Al-Refaie et al., 2015). An effective technique for measuring processes’ relative efficiency is the Data envelopment analysis (DEA) method, in which a production frontier is constructed from a set of comparable Decision making Units (DMUs) and data on their inputs and outputs. The efficiency of each DMU is deðned by its relative distance from the production frontier (Al-Refaie et al., 2016a; Al-Refaie et al., 2016b; Ennen and Batool, 2018). Two common DEA models can be used for this purpose Charnes, Cooper, and Rhodes (CCR) and Banker, Chang, and Cooper (BCC) by Charnes et al. (1978) and Banker et al. (1984), respectively.
However, when using the CCR and BCC models, an important rule of thumb is that the number of DMUs is at least twice the sum of the number of inputs and outputs (Arcos-Vargaset al., 2017). Otherwise, the model may produce numerous relatively efficient units and decrease discriminating power. To resolve this difficulty, DEA window analysis was introduced in which the performance of a DMU in any period can be compared with its own performance in other periods as well as to the performance of other DMUs (Al‐Refaie et al., 2014). DEA window analysis is based on a dynamic perspective, regarding the same DMU in different period of time as entirely different DMUs (Jia and Yuan, 2017). The window analysis technique relies on the traditional CCR and BCC models for estimating technical efficiency (TE) and pure technical efficiency (PTE) scores for each DMU. DEA window analysis is usually followed by the evaluation of the Malmquist productivity index (MPI), which is a formal time-series analysis method for conducting performance comparisons of DMUs over time by solving traditional DEA type models. The MPI measures the productivity change of DMU over time. The productivity of DMU from period p and p+1 is improved when MPI is larger than one, remained unchanged when MPI equals one, and deteriorated when MPI is less than one. The productivity change can be decomposed into two parts, namely technological change (TC) and efficiency change (TEC) component, which measures the change in relative efficiency over time (Balcerzak et al., 2017).