Efficiency analysis accounting for internal and external non-discretionary factors

Abstract

This paper develops a method based on data envelopment analysis (DEA) for efficiency assessments taking into account the effect of non-discretionary factors. A typology that classifies the non-discretionary factors into two groups is proposed: the factors that characterize the external conditions where the decision making units (DMUs) operate (external factors), and the factors that are internal to the production process but cannot be controlled by the decision makers (internal factors). This paper proposes an enhanced DEA model that accommodates non-discretionary inputs and outputs and treats them differently depending on their classification as internal or external to the production process. This generalized model integrates the previous approaches for dealing with non-discretionary variables described in the DEA literature. The model defines the efficient frontier based exclusively on the discretionary variables and internal non-discretionary factors, but the potential peers of each DMU are restricted to other units facing comparable external conditions (represented by the external nondiscretionary factors). The peer selection criteria implemented in the DEA model is informed by decision makers' opinion. The applicability of the model developed is illustrated with a real-world assessment of retailing stores.

Performance comparison of retailing stores using a Malmquist-type index

“…Concerning food-based outlets, few studies analysed the performance of multiple stores within the same organisation, such as Keh and Chu (2003), Barros and Alves (2004), Camanho et al (2009) and Vaz et al (2010), which analysed supermarkets from an organisation. DEA was also used to assess the efficiency of supermarket chains by Athanassopoulos and Ballantine (1995).…”

“…Next, we describe the main input and output measures used in previous DEA studies of retailing services. The main inputs used were floor area, number of employees, stock and operational expenses (see Athanassopoulos and Ballantine, 1995;Thomas et al, 1998;Grewal et al, 1999;Keh and Chu, 2003;Barros and Alves, 2004;Camanho et al, 2009). The outputs can include sales value (in Athanassopoulos and Ballantine, 1995;Grewal et al, 1999;Keh and Chu, 2003;Camanho et al, 2009), sales value and profit (in Thomas et al, 1998) or sales value and operational results (in Barros and Alves, 2004).…”

Efficiency and Productivity Assessment of Wind Farms

“…The inclusion of this non-discretionary input assures that a farm with unfavorable conditions regarding wind resource is not penalized in the performance assessment. The wind hours is an internal non-discretionary input which should be used for the definition of the PPS, according to [2]. Data concerning the maintenance schemes and operation costs are confidential and, consequently, they are not included in the model.…”

A Method to Deal with Dissimilar Circumstances of Public Organizations in Performance Comparisons: Evidence from Dutch Prisons

“…Their first Data Envelopment Analysis model (DEA) assumed that the inputs and outputs were entirely under managerial control. In the last decade, there is growing attention for the problem that a score on a performance measure is not necessarily a result of managerial effort in full (e.g., Fried et al, 2002;Camanho, Portela & Vaz, 2009). …”

“…Differences in performance scores may stimulate inferior performing organizations to make efforts for better performance, e.g. via benchmarking principles (see Camp, 1989). In his consolidated view of reasons for measuring performance, Pidd (2013) suggests six categories: planning and improvement, monitoring and control, evaluation and comparison, accountability, financial budgeting and planning, and individual performance management.…”