摘要：In this issue, the editor will introduce the result (2) of the journal article "Decarbonised closed-loop supply chains resilience:
分享兴趣，传播快乐，
增长见闻，留下美好。
亲爱的您，这里是LearningYard学苑！
今天小编为您带来文章
“慧学（38）：精读期刊论文’Decarbonised closed-loop supply chains resilience: examining the impact of COVID-19 toward risk mitigation by a fuzzy multi-layer decision-making framework’结果（2）”
欢迎您的访问！
Share interest, spread happiness,
increase knowledge, and leave beautiful.
Dear, this is the LearingYard Academy!
Today, the editor brings the
"Hui Xue (38): Intensive reading of the journal article
'Decarbonised closed-loop supply chains resilience: examining the impact of COVID-19 toward risk mitigation by a fuzzy multi-layer decision-making framework' result (2)"
Welcome to visit!
本期推文小编将从思维导图、精读内容、知识补充三个方面为大家介绍期刊论文《Decarbonised closed-loop supply chains resilience: examining the impact of COVID-19 toward risk mitigation by a fuzzy multi-layer decision-making framework》的结果（2）。
In this issue, the editor will introduce the result (2) of the journal article "Decarbonised closed-loop supply chains resilience: examining the impact of COVID-19 toward risk mitigation by a fuzzy multi-layer decision-making framework" from three aspects: mind mapping, intensive reading content, and knowledge supplement.
一、思维导图（Mind mapping）
二、精读内容（Intensive reading content）
1、动力图结果（Dynamic graph results）
在悲观情境与最可能情境下，13项评价指标的分类结果保持一致，被划分为三大类型：独立类（TAs、CRI、MRI、RMM）、联系类（LTs、TandL、W）和依赖类（T、F、TCs、SBC、POP、EP）。然而在乐观情境中，分类情况有所不同，标准仅分为两类：独立类（RMM、TAs、MRI）以及联系类（T、F、TCs、SBC、LTs、TandL、POP、EP、W、CRI）。需要强调的是，在三种情境下，自主类始终未出现，这一发现从侧面验证了 fuzzy-Delphi 方法具备较高的稳健性与可靠性。
In both the pessimistic and most likely scenarios, the classification results for the 13 evaluation indicators remained consistent, falling into three main categories: independent (TAs, CRI, MRI, RMM), connected (LTs, TandL, W), and dependent (T, F, TCs, SBC, POP, EP). However, in the optimistic scenario, the classification differed, with the criteria falling into only two categories: independent (RMM, TAs, MRI) and connected (T, F, TCs, SBC, LTs, TandL, POP, EP, W, CRI). It is important to note that the independent category did not appear in any of the three scenarios, a finding that indirectly validates the robustness and reliability of the fuzzy-Delphi method.
2、层级关系（Hierarchical relationship）
在层级结构上，悲观与最可能两种情境下，13项评价标准被划分为六个层次，呈现出较为复杂的多级分布。而在乐观情境中，结构则明显简化，仅形成两个层次：第一层包括除RMM与MRI外的所有生态、经济和工业类标准；第二层则由RMM、MRI以及技术类标准构成，并对第一层的10项标准产生显著影响。由此可见，乐观情境下的层级关系更为简明，但技术类标准在系统中的主导作用得到进一步凸显。
In terms of the hierarchical structure, the 13 evaluation criteria in both the pessimistic and most likely scenarios are divided into six levels, presenting a relatively complex multi-level distribution. In the optimistic scenario, however, the structure is significantly simplified, forming only two levels: the first level includes all ecological, economic, and industrial criteria except for RMM and MRI; the second level consists of RMM, MRI, and technical criteria, which significantly influence the 10 criteria in the first level. This shows that the hierarchical relationship is simpler in the optimistic scenario, but the dominant role of technical criteria in the system is further highlighted.
3、悲观、最可能、乐观情境对比（Comparison of pessimistic, most likely, and optimistic scenarios）
在悲观与最可能情境下，F-DEMATEL将TAs、RMM、MRI和CRI判定为原因组，而F、T、TCs、EP、SBC和POP被划入结果组，LTs被视为原因因素，W与TandL则归为结果因素。相较之下，F-ISM-MICMAC则认为LTs、W和TandL同时具备因果属性，体现了两种方法在部分标准分类上的差异。进入乐观情境后，这种差异更加显著：F-DEMATEL仍将TAs、RMM、MRI和CRI归类为原因，而F、T、TCs、SBC、TandL、POP、EP与W则被视为结果，LTs也由原因转变为结果；然而，F-ISM-MICMAC却认定除TAs、RMM和MRI外，其余标准均具有因果双重属性。总体来看，两种方法在不同情境下既存在一定一致性，也表现出差异性，其中乐观情境下的不一致更为突出。
In the pessimistic and most likely scenarios, F-DEMATEL classifies TAs, RMM, MRI, and CRI as causal factors, while F, T, TCs, EP, SBC, and POP are assigned to the outcome group. LTs are considered causal factors, while W and TandL are classified as outcome factors. In contrast, F-ISM-MICMAC considers LTs, W, and TandL to have both causal properties, reflecting the differences in the classification of some criteria between the two methods. This difference becomes more pronounced in the optimistic scenario: F-DEMATEL still classifies TAs, RMM, MRI, and CRI as causal factors, while F, T, TCs, SBC, TandL, POP, EP, and W are considered outcomes. LTs also shift from being a cause to an outcome. However, F-ISM-MICMAC identifies all criteria, except TAs, RMM, and MRI, as having dual causal properties. Overall, the two methods exhibit both consistency and differences across different scenarios, with the inconsistency being more pronounced in the optimistic scenario.
4、差异与互补（Differences and complementarities）
进一步分析表明，两种方法在因果关系的识别上存在一定差异。例如，F-DEMATEL捕捉到了MRI对CRI的影响，而这一关系在F-ISM-MICMAC中并未体现；相反，TAs对CRI的作用则仅由F-ISM-MICMAC揭示，而在F-DEMATEL中缺失。此外，F-ISM-MICMAC还发现了生态类与经济类标准之间的互动关系，以及W对EP的影响，这些联系同样未被F-DEMATEL识别。总体来看，这些差异说明两种方法在结果上具有互补性。
Further analysis revealed some differences between the two methods in identifying causal relationships. For example, F-DEMATEL captured the effect of MRI on CRI, a relationship not reflected in F-ISM-MICMAC. Conversely, the effect of TAs on CRI was revealed only by F-ISM-MICMAC but not by F-DEMATEL. Furthermore, F-ISM-MICMAC identified interactive relationships between ecological and economic criteria, as well as the effect of W on EP, relationships also not identified by F-DEMATEL. Overall, these differences suggest that the two methods yield complementary results.
5、综合结论（Comprehensive conclusion）
总体来看，F-DEMATEL的因果划分与F-ISM-MICMAC的驱动—依赖关系在逻辑上保持一致，两种方法相互印证，从而提升了研究结论的可信度。尽管个别标准（如LTs）在不同情境下的角色发生了转变，但整体趋势仍较为稳定：在悲观和最可能情境中，LTs作为原因因素展现出较强的驱动力，而在乐观情境下则转变为结果因素，其依赖性随之增强。通过对比并结合这两种方法，本文不仅验证了分析结果的稳健性与可靠性，也为后续的理论研究和实践管理提供了更加清晰且有力的参考。
Overall, the F-DEMATEL causal delineation and the F-ISM-MICMAC driver-dependency relationship are logically consistent, and the two approaches reinforce each other, thus enhancing the credibility of the research conclusions. Although the role of individual criteria (such as LTs) shifts across scenarios, the overall trend remains relatively stable: in the pessimistic and most likely scenarios, LTs exhibit a stronger driving force as causal factors, while in the optimistic scenario, they shift to being outcome factors, with their dependence increasing accordingly. By comparing and combining these two approaches, this paper not only verifies the robustness and reliability of the analytical results but also provides a clearer and more powerful reference for subsequent theoretical research and practical management.
三、知识补充（Knowledge supplementation）
1、数据分析中因果关系定义（Defining causality in data analysis）
因果关系是指某一事件（因）直接导致另一事件（果）的发生，两者之间存在明确的时间顺序和逻辑联系。在数据分析中，因果关系的识别具有重要作用：它不仅能够揭示变量之间的直接影响路径，还能为科学决策提供依据，避免将相关性误判为因果性。同时，对因果关系的探究有助于实验和模拟的合理设计，从而更有效地验证研究假设，并提升模型的解释力与预测精度。
Causation refers to the direct relationship between one event (cause) and another (effect), with a clear temporal sequence and logical connection between the two. Identifying causal relationships plays a crucial role in data analysis: it not only reveals the direct influence paths between variables but also provides a basis for scientific decision-making, avoiding the misinterpretation of correlation as causation. Furthermore, exploring causal relationships facilitates the rational design of experiments and simulations, enabling more effective validation of research hypotheses and enhancing the explanatory power and predictive accuracy of models.
2、稳健性概述（Robustness overview）
稳健性最初是数理统计学中的术语，用以描述统计方法在假设条件发生偏离时仍能保持有效性的能力。20世纪70年代，该概念被引入控制理论，用于刻画系统对参数扰动的不敏感性。在统计学领域，稳健性体现为方法对总体假设变化或数据偏差的适应性，常见的实现方式包括M估计、R估计和L估计，其性能可通过影响函数与崩溃点等指标加以度量。在会计学中，稳健性原则成为企业会计核算的重要准则，强调对可能损失的确认与对不确定收入的审慎处理，以应对市场风险。在金融研究中，稳健性评价指标被用于监测和预测系统性金融风险，这类定量分析方法同样为经济管理中的模型误设评估提供了解决思路。在控制理论中，稳健性分析被广泛应用于慢时变系统的适应控制设计，并在自动化与信号处理等领域用于指导在可检测性不足情况下的最优决策规则构建。由此可见，稳健性已成为跨学科的重要方法论范式，对推动统计学、经济管理学与工程技术的发展均具有深远意义。
Robustness was originally a term in mathematical statistics, describing the ability of a statistical method to maintain its validity despite deviations from its assumptions. In the 1970s, the concept was introduced into control theory to characterize a system's insensitivity to parameter perturbations. In statistics, robustness is reflected in a method's adaptability to changes in overall assumptions or data deviations. Common implementations include M-estimation, R-estimation, and L-estimation, with performance measured using metrics such as influence functions and breakdown points. In accounting, the principle of robustness has become a key criterion in corporate accounting, emphasizing the recognition of potential losses and the prudent treatment of uncertain income to address market risks. In financial research, robustness evaluation indicators are used to monitor and predict systemic financial risks. This type of quantitative analysis also provides solutions for assessing model misspecification in economic management. In control theory, robustness analysis is widely used in the design of adaptive control for slowly time-varying systems and in fields such as automation and signal processing to guide the construction of optimal decision rules in situations where detectability is insufficient. Robustness has thus become an important interdisciplinary methodological paradigm, with profound implications for the advancement of statistics, economic management, and engineering.
今天的分享就到这里了，
如果您对文章有独特的想法，
欢迎给我们留言，
让我们相约明天。
祝您今天过得开心快乐！
That's all for today's sharing.
If you have a unique idea about the article,
please leave us a message,
and let us meet tomorrow.
I wish you a nice day!
翻译：Google翻译
参考资料：百度、Chatgpt
参考文献： Hannan Amoozad Mahdiraji, Fatemeh Yaftiyan,Jose Arturo Garza-Reyes, et al. Decarbonised closed-loop supply chains resilience: examining the impact of COVID-19 toward risk mitigation by a fuzzy multi-layer decision-making framework [J]. Annals of Operations Research, 2024, 1(1): 1-45.
本文由LearningYard学苑整理发出，如有侵权请在后台留言！
文案|chen
排版|chen
审核|hzy
来源：LearningYard学苑