一般灰数型面板数据关联分析模型及应用

Relational analysis model and its application for general grey number panel data

对于由一般灰数型面板数据的指标排列顺序变换引起的灰色关联序不一致问题,构建了灰色重心三角曲面关联分析模型。首先,基于排列组合原理将样本矩阵分解为二元指标子矩阵,并给出样本矩阵的一般灰数元素的核和上下界。其次,给出由二元指标子矩阵相邻四点的上下界所确定的几何体的重心,并确定了由核及重心所构成的空间重心三角曲面。然后,以空间重心三角曲面作为曲顶的柱体体积,构建了关联系数公式,得到一般灰数型面板数据的灰色关联分析模型。最后,将所提模型应用于复杂装备供货商的选择问题,验证了所提模型的合理性和有效性。

To solve the problem of inconsistent grey relational order caused by the index order transformation of general grey number panel data,a grey centroid triangular surface relational analysis model is built.Firstly,based on the permutation and combination principle,the sample matrix is decomposed into binary index submatrices,and the kernel and upper and lower bounds of the general grey number elements of the sample matrix are given.Secondly,the center of gravity of the geometry determined by the upper and lower bounds of the adjacent four points of the binary index submatrix is given,and the spatial center of gravity triangle surface composed of the kernel and the center of gravity is determined.Then,based on the volume of the cylinder with the triangular surface of the spatial center of gravity as the curved top,the relational coefficient formula is constructed,and the grey relational analysis model of the general grey number panel data is obtained.Finally,the proposed model is applied to the selection problem of complex equipment suppliers to verify its rationality and effectiveness.