基于灰熵法的公路货运量和货物周转量关联因素分析
Analysis of relavent factors for highway freight volume and freight turnover based on grey entropy method

分析了国民经济宏观因素与公路货运量和货物周转量之间的相互影响,提出了基于灰色关联度算法与熵权法相结合的灰熵关联度算法,依据《陕西统计年鉴》中近14年的经济数据与公路货运量和货物周转量数据,研究了国民经济宏观因素与公路货运量和货物周转量之间的关联系数,给出了各个经济指标对公路货运量和货物周转量的影响程度; 去除各数据之间量纲的影响,用灰色关联度算法计算经济指标与公路货运量和货物周转量之间的关联系数,用熵权法计算各经济指标的权重; 基于经济指标的关联系数及其权重,计算了各个经济指标与公路货运量和货物周转量之间的关联度,并分析了北京市和天津市公路货运量的影响因素。分析结果表明:对于经济指标,公路货运量和货物周转量呈现相似的关联趋势,陕西省公路货运量与第一产业产值、工业增加值、第二产业产值之间的关联度较高,分别为0.944 7、0.941 7、0.940 2,货物周转量与第一产业产值、城镇单位在岗职工平均工资、人均生产总值的关联度较高,分别为0.920 7、0.915 9、0.915 3; 北京市公路货运量与第三产业指数、第二产业指数、人均生产总值指数的关联度较高,分别为0.716 2、0.714 8、0.710 9; 天津市公路货运量与城镇单位在岗职工平均工资、生产总值、第三产业产值、第二产业产值、工业增加值、人均生产总值的关联度较高,分别为0.862 0、0.855 6、0.853 4、0.851 4、0.851 4、0.851 3。可见:北京市与天津市公路货运量关联因素分析结果总体上同陕西省基本一致,主要关联因素都是该地区三大产业产值。
The interaction effects between the national macro-economic factors and highway freight volume and freight turnover were analyzed. A grey entropy relational degree algorithm based on the grey relational degree algorithm and the entropy weight method was proposed. According to the economic data and highway freight volume and freight turnover data of Shaanxi Statistical Yearbook in the past 14 years, the relevant coefficients between the national macro-economic factors and highway freight volume and freight turnover were studied, and the influence degree of each economic indicator on highway freight volume and freight turnover was obtained. By removing the dimensional effect between the data, the relevant coefficients between the economic indicators and highway freight volume and freight turnover were calculated by the grey relational degree algorithm,and the weights of the economic indicators were calculated using the entropy weight method. The relevant degrees between the economic indicators and highway freight volume and freight turnover were calculated based on the relevant coefficients of the economic indicators and their weights. Moreover, the influencing factors of the highway freight volumes in Beijing and Tianjin were analyzed. Analysis result shows that for the economic indicators, the highway freight volume and freight turnover show similar relevant trends. In Shaanxi Province, the relational degrees between the highway freight volume and output value of the primary industry, added value of the industry and output value of the secondary industry are relatively higher, and are 0.944 7, 0.941 7, and 0.940 2, respectively. The relational degrees between the freight turnover and output value of the primary industry, average salary of the on-job employees in the urban units, and per capita GDP are higher, and are 0.920 7, 0.915 9, and 0.915 3, respectively. In Beijing, the