水文频率分析的非参数统计计算方法  

Nonparametric Statistics Models of Hydrologic Frequency Analysis

作　　者：董洁[1] 谭秀翠[1] 张庆华[1] 刁艳芳[1] 徐妍 DONG Jie;TAN Xiu-cui;ZhANG Qing-hua;DIAO Yan-fang;XU Yan(College of Water Conservancy and Civil Engineering,Shandong Agricultural University,Taian 271018,Shandong Province,China)

机构地区：[1]山东农业大学水利土木工程学院,山东泰安271018

出　　处：《中国农村水利水电》2018年第7期5-8,14,共5页China Rural Water and Hydropower

基　　金：国家自然科学基金资助(41202174;41771282)

摘　　要：为了改进了非参数统计依靠大样本保证精度,避开参数统计中水文频率分析计算的线型假设问题。以非参数统计理论为基础,把变换理论和非参数统计理论结合起来,提出了一种直接对经验分布函数拟合的非参数回归的变换方法,并将其用于水文频率分析计算。蒙特卡罗统计试验结果表明,该方法是合理的,为水文频率分析提供了一种有效方法。In order to improve the accuracy of nonparametric statistics relying on large samples,avoid the linear hypothesis problem of hydrologic frequency analysis calculation in parametric statistics,this paper proposes a nonparametric regression transformation method of directly fitting empirical distribution function based on the nonparametric statistic theory and combined with transformation theory,which will be applied in hydrologic frequency analysis. Checked by Monte Carlo Statistical Test,this method,with good robustness,provides another effective way for hydrologic frequency analysis calculation.

关 键 词：非参数回归 核估计 窗宽 水文频率 

分 类 号：TV122[水利工程—水文学及水资源]