对使用主成分进行绩效指标值排名的讨论

对《基于数据的Goodgrant基金最优投资策略》一文使用主成分分析进行综合评价,对候选学校绩效指标值排名进行了探讨。首先,综合前人研究与本题实际,指出使用主成分分析进行综合评价存在的争议与不足;然后,分别建立TOPSIS模型和综合评价模型对候选学校的绩效指标值进行排名,并对不同方法得到的结果进行对比。结果表明,TOPSIS模型和综合评价模型得到的排名具有高度一致性,前50名重合率达98%,而与主成分分析综合评价的重合率仅有6%,说明使用TOPSIS等传统评价模型对候选学校绩效指标值进行排名更合适。

The Discussion of Performance Index Ranking with the Principal Component Analysis Comprehensive Evaluation Model

This paper discusses the performance index ranking of the schools through the principal component analysis comprehensive evaluation model in "Optimal strategy of donation for Goodgrant charitable organization based on data".Firstly,we point out the existing disputes and disadvantages of using principal component analysis comprehensive evaluation model according to the previous research and the practical problem.Then we establish TOPSIS model and comprehensive evaluation model to rank candidate schools'' performance index respectively,and compare the results of the different models.The results show that TOPSIS model has a high degree of consistency with comprehensive evaluation model,the top 50 coincidence rates are as high as 98% with comprehensive evaluation model while only 6% with principal component analysis comprehensive evaluation model.Finally,we get the conclusion that it is better to use TOPSIS model to rank candidate schools'' performance index.