Pitfalls and Remedies in DEA Applications: How to Handle an Occurrence of Zero in Multipliers by Strong Complementary Slackness Conditions

Abstract

This study discusses a guideline on a proper use of Data Envelopment Analysis (DEA) that has been widely used for performance analysis in public and private sectors. The use of DEA is equipped with Strong Complementary Slackness Conditions (SCSCs) in this study, but an application of DEA/SCSCs depends upon its careful use, as summarized in the guideline. The guideline consists of the five suggestions. First, a data set used in the DEA applications should not have a ratio variable (e.g., financial ratios) in an input(s) and/or an output(s). Second, radial DEA models under variable and constant Returns to Scale (RTS) need a special treatment on zero in a data set. Third, the DEA evaluation needs to drop an outlier. Fourth, an imprecise number (e.g., 1/3) may suffer from a round-off error because DEA needs to specify it in a precise expression to operate a computer code. Finally, when a large input or output variable may dominate other variables in DEA computation, it is necessary to normalize the data set or simply to divide each observation by its average. Such a simple treatment produces more reliable DEA results than the one without any data adjustment. This study also discusses how to handle an occurrence of zero in DEA multipliers by applying SCSCs. The DEA/SCSCs can serve for a multiplier restriction approach without any prior information. Thus, the propesed DEA/SCSCs can provide more reliable results than a straight use of DEA.

Approaching Effects of the Economic Crisis on University Efficiency - A Comparative Study of Germany and Italy

“…Some universities do not generate patents or publications in some points of time in the observed timeframe. We orientate on Sueyoshi and Goto (2013) and Thompson, Dharmapala, and Thrall (1993) and add a small number (0.1) for zero values. As our main goal consists in measuring the efficient translation of state efforts to the three missions, we will use state funding as an 11 input (Agasisti & Pohl, 2012;Kempkes & Pohl, 2010).…”

Does Technological Innovation Efficiency Improve the Growth of New Energy Enterprises? Evidence from Listed Companies in China

“…Firstly, existing studies mainly adopt the DEA method to measure technological innovation efficiency because it does not require pre-set production functions and the analysis process is convenient. However, the traditional DEA model cannot distinguish the impact of the external environment and random errors, is sensitive to outliers, and is easily affected by extreme values, making it difficult to achieve an objective evaluation [52]. Therefore, in order to reduce the impact of random errors on measurement results, control the fluctuation of outliers caused by "black swan events" such as COVID-19, and improve the calculation accuracy of panel data, it is necessary to conduct research on technological innovation efficiency based on parametric methods such as SFA [53].…”

Performance Assessment in the Bioenergy Field: Evidence from European Countries

“…If discussing drawbacks, it is necessary to substantiate the fact that the DEA method is very broad and general. Along time many authors tried to highlight strengths and weaknesses of DEA method (Stolp, 1990), advantages and disadvantages (Fenyves & Tarnóczi, 2020;Jordá, Cascajo, & Monzón, 2012), demonstrating pitfalls after applying it (Sueyoshi & Goto, 2013;Wojcik, Dyckhoff, & Clermont, 2019). The number of direct jobs includes equipment production, plant construction, engineering and management, operation and maintenance, supply and exploitation of biomass.…”