城市火灾次数与气象因子的分位数回归分析  

Quantile regression analysis of the number of urban fires and meteorological factors

作　　者：刘盼盼[1] 周嘉章[2] 谭常春[1] 

机构地区：[1]合肥工业大学数学学院,安徽合肥230009 [2]安徽省气象局培训中心,安徽合肥230031

出　　处：《合肥工业大学学报（自然科学版）》2013年第10期1273-1277,共5页Journal of Hefei University of Technology：Natural Science

基　　金：安徽省自然科学基金资助项目(1208085QA12);全国统计科学研究计划资助项目(2012LZ009);教育部人文社会科学研究基金资助项目(12YJC910007)

摘　　要：文章基于某市1997—2007年间的火灾数据,采用分位数回归方法,从月平均温度、月平均湿度、月平均风速及月平均降水量4个方面对月火灾次数进行实证分析。结果表明:各气象因子对火灾次数的影响具有一定的季节规律,温度在夏季对火灾次数影响比较显著,湿度和降水量在冬季对火灾次数影响较显著,而风速在各季节对火灾次数的影响均不显著。.Based on a city＇s fire data of 1997-2007, the quantile regression approach is adopted to em- pirically investigate the monthly fire number from four aspects including monthly average tempera- ture, monthly average relative humidity, monthly average wind speed and monthly average rainfall. The results show that the influence of the meteorological factor on fire number has certain season rule. The temperature exerts a more important effect on fire number in summer. Humidity and rain- fall have a more significant impact on fire number in winter. However, wind speed has no obvious function on fire number in any season.

关 键 词：分位数回归 火灾次数 气象因素 OLS估计 

分 类 号：O212.1[理学—概率论与数理统计]