论文部分内容阅读
利用因子分析法对日本2005年统计数据进行了分析。从13个常用火灾统计指标中提取出火灾后果总量、火灾发生概率、平均死亡人数及平均经济损失4个公因子,并采用多元线性回归方法对若干社会经济因素与4个公因子建立多元线性模型。根据模型的判定系数和各自变量的偏相关系数,分析了若干社会经济因素与4个火灾风险公因子的相关性并对重要度进行排序。结果表明,4个公因子意义明确且相互独立,可全面表征城市火灾风险程度。基于分析数据,火灾后果总量公因子与人口总量呈显著线性相关;火灾发生率公因子主要受人员结构、人口流动性及居住条件3个方面影响,与人口总量、经济水平、教育水平之间不存在线性相关性;平均死亡人数公因子随消防训练提高而显著降低;平均经济损失公因子与选用的任何一个社会经济因素之间都没有线性相关性。
Japan’s 2005 statistics were analyzed by factor analysis. Four common factors of total fire consequences, fire occurrence probability, average death toll and average economic loss were extracted from 13 commonly used fire statistics indexes. Multiple linear regression methods were used to establish multiple linearity of some social economic factors and 4 common factors model. According to the model’s coefficient of determination and the partial correlation coefficient of each variable, the correlation between several socio-economic factors and four common fire risk factors is analyzed and the importance is sorted. The results show that the four common factors have clear and independent meanings and can fully characterize the degree of urban fire risk. Based on the analysis data, the commonality factor of the total aftermath of the fire is significantly linearly correlated with the total population. The common factor of the fire incidence is mainly affected by the personnel structure, the mobility of the population and the living conditions. The common factor of the total population, the economic level, the education level There is no linear correlation between them; the common factor of average death toll decreases significantly with fire fighting training; and there is no linear correlation between the common economic loss factor and any of the selected socio-economic factors.