关键词: 空战威胁评估, 指标关联, CRITIC法, 线性回归分析, 相对贴近度

Abstract: In view of the subjectivity of using index weight determination in the process of air combat threat assessment and the neglect of the internal relationship between the indexes，a calculation method of determining the index weight based on an improved criteria importance though intercriteria correlation- linear regression analysis (CRITIC-LRA) is proposed. The Gini coefficient and Kendall correlation coefficient are introduced to improve the CRITIC method and determine the initial weight of indexes in accordance with the defects of CRITIC; the first-order linear regression analysis(LRA) is used to calculate the correlation of evaluation indexes, and the indexes relevance is reduced by decreasing the index weight.In order to overcome the shortcomings of using Euclidean distance as a distance measure in the technique for order performance by similarity to ideal solution (TOPSIS)，the weighted grey correlation degree between indexes is used to replace Euclidean distance，and the relative closeness degree is calculated to achieve the target threat ranking. The threat assessment example shows that the proposed method can fully reflect the target threat differentiation and rank the targets.

Key words: aircombatthreatassessment, indexcorrelation, criteriaimportancethoughintercritieriacorrelationmethod, linearregressionanalysis, relativecloseness