Development and Evolution of Slacks‐Based Measure Models in Data Envelopment Analysis: A Comprehensive Review of the Literature
综述了非参数数据包络分析框架下基于松弛的测度（SBM）模型的发展与改进方向，包括输入输出特性、数据特殊性、超效率排序、网络结构、动态分析等，适合研究效率评价方法的学者快速了解该领域进展。
ABSTRACT This paper provides a comprehensive review of slacks‐based measure (SBM) models within the nonparametric data envelopment analysis (DEA) framework. The review reveals that the development and modifications of SBM models have progressed in multiple directions. Key areas of modification include (1) the nature of inputs and outputs, (2) data specificity, (3) super‐efficiency for ranking decision‐making units, (4) the inclusion of networks in organizational structures or production processes, (5) the dynamic nature of the analysis, and (6) various other methodological aspects. Increasingly, complex SBM models addressing multiple aspects, such as input/output characteristics and data specificity, are appearing in the literature. Another notable trend is the integration of various methodological proposals from different authors into unified SBM models. Some publications even attempt to forecast future efficiency levels and incorporate large datasets (big data). Despite numerous modifications and advancements, SBM models still lack robust statistical inference capabilities, unlike radial models, which possess more developed statistical foundations.