Using Data Envelopment Analysis to Evaluate Effectivity: A Scoping Review

Background. This paper presents a scoping review of DEA literature to identify the different applications, methodologies, and challenges in using DEA for efficiency evaluation. Purpose. The purpose of this scoping review is to provide an overview of the literature on Data Envelopment Analysis (DEA) and its applications, methodologies, and challenges in evaluating the efficiency of decision-making units (DMUs) in various fields. Materials and Methods. The scoping review methodology was used to identify relevant literature on DEA and its applications. The search was conducted in several electronic databases, including Scopus, Web of Science, and Google Scholar, using keywords such as "Data Envelopment Analysis," "DEA," "efficiency," "performance evaluation," and "decision-making units." The inclusion criteria for the articles were that they should be published in English, peer-reviewed, and focus on DEA and its applications in various fields. The exclusion criteria were articles that were not relevant to the topic or not meeting the inclusion criteria. Results. The search resulted in 456 articles, of which 195 were duplicates. After screening the titles and abstracts, 207 articles were excluded as they did not meet the inclusion criteria. The full texts of the remaining 54 articles were reviewed, and 10 articles were excluded as they did not provide sufficient information on DEA or its applications. Finally, 44 articles were included in the scoping review. The articles were analyzed using a thematic analysis approach, which involved identifying themes and sub-themes related to DEA and its applications. The themes identified were DEA models, input and output selection, sensitivity analysis, applications of DEA, challenges associated with DEA, and future research directions. Conclusion. The scoping review found that DEA is widely used in various fields, including healthcare, education, finance, and agriculture. Different types of DEA models, such as CCR, BCC, SBM, and FDH models, are employed. The selection of input and output variables is crucial and can be done through expert judgment, statistical methods, or stakeholder consultation. Sensitivity analysis is important for testing robustness and identifying influential variables. Challenges identified include data quality, model specification, and result interpretation. Future research directions include hybrid models combining DEA with other techniques and exploring DEA in sustainability and social responsibility. Overall, the review provides a comprehensive overview of DEA's applications, methodologies, challenges, and future directions.