基于改进CRITIC的修正G2赋权方法及实证  

Modified-G2 Weighting Method Based on Improved CRITIC and Its Solid Evidence

作　　者：祝志川[1,2] 张国超 张君妍 Zhu Zhichuan;Zhang Guochao;Zhang Junyan(Faculty of Statistics,Jinlin University of Finance and Economics,Changchun 130117,China;School of Mathematics and.Statistics,Northeast Normal University,Changchun 130024,China)

机构地区：[1]吉林财经大学统计学院,长春130117 [2]东北师范大学数学与统计学院,长春130024

出　　处：《统计与决策》2018年第18期33-38,共6页Statistics & Decision

基　　金：国家自然科学基金资助项目(11690012);吉林省社会科学基金资助项目(2016BS13);吉林省科技发展计划资助项目(20170520050JH);吉林财经大学基金资助项目(2016Z10;2016Q31)

摘　　要：为了使评价结果既能反映专家经验又可反映客观数据信息,同时兼顾指标的横向影响程度与纵向变异程度,文章分别利用各评价指标与最不重要指标的改进CRITIC信息量或置信区间上下限之比代替人为主观确定重要性程度之比的理性赋值,构造了两种新的基于改进CRITIC信息量的修正G2点赋值和区间赋值权重计算方法。同时,运用新构造的赋权方法建立了区域“五化”同步发展模糊综合评价模型,并以吉林省为例进行了实证分析。In order to make the evaluation rcsuhs reflect both expert experience and objective data information, simultaneously considering both the transverse influence degree and longitudinal change degree, this paper uses the ratio of each evaluation index to the modified CRITIC information quantity or upper and lower limit of eonfidence interval of the least importanl index to replace the subjective man-made rational assignment of the importance ratio between these two evaluation indexes, and constructs two new methods for calculating the modified G2 point and interval weight based on improved CRITIC information quantity. At the same time the paper uses the newly proposed weighting method to build a fuzzy synthetic evaluation model of area ＂Five Target＂ coordinated development, and finally takes Jilin Province as an example for an empirical analysis.

关 键 词：G2法 改进CRITIC法 赋权方法 模糊综合评价 

分 类 号：N945.16[自然科学总论—系统科学] O212.4[理学—概率论与数理统计]