Abstract: A new method called gray correlation analysis method based on DEA (Data Envelopment Analysis) is presented to evaluate the regional highway network. It integrates favorable aspects of both DEA and gray correlation analysis, and takes the latter as a central model. DEA determines the weight vector of correlation coefficients for each Decision-Making Unit (DMU) to calculate the relatively optimal correlation degrees and then realizes the priority order of the objects. This method can avoid the subjectivity when the weight vector is determined and get the optimality of the prior order evaluation by non-uniform weight. Finally, an example of highway network assessment of some provinces in China is given to prove the validity of the method.

Key words: data envelopment analysis (DEA), gray correlation analysis, regional highway network, comprehensive evaluation

摘要： 提出了一种基于数据包络分析（DEA）和灰色关联分析的区域公路网评价方法。该方法综合了DEA和灰色关联分析两种方法的优势，以灰色关联分析为中心模型，通过复合DEA模型来确定每一个被评价对象（决策变量）中各点关联系数的权重向量，从而计算出相对最优的关联度，实现对评价对象客观的优先排序。该方法不但能克服确定权重时的主观性，而且通过对各指标的“非均一”赋权，有利于达到优先序评价的“最优性”。最后通过对我国部分省区公路网的评价实例说明了方法的有效性。

关键词: 数据包络分析, 灰色关联分析, 区域公路网, 综合评价