线性矩法估计参数的保证修正值系数B的推求  

Deriving the B Nomogram of L-Moments Method to Estimate Sampling Errors of Design Floods

作　　者：刘攀[1] 郭生练[1] 胡安焱[1] 

机构地区：[1]武汉大学水资源与水电工程科学国家重点实验室,湖北武汉430072

出　　处：《水文》2006年第6期27-29,共3页Journal of China Hydrology

基　　金：水利部重大科研项目<水库设计运用专题研究>;湖北自然科学基金(2006ABA229)

摘　　要：在设计洪水的抽样误差估计中,采用保证修正值系数B方法估计均方差简单易用。应用线性矩法估计频率分布曲线的参数,有较好的无偏性和有效性,具有一定的应用前景。目前线性矩法的B值诺模图尚未确定,给用线性矩法确定参数时估计抽样误差带来了难度与不便。采用统计试验,分析了离差系数、偏态系数和样本长度对B值的影响,结果表明线性矩法估计参数时仍可采用保证修正值系数B值诺模图方法来估计抽样误差,并推求了不同偏态系数、设计频率情形下的B值,制成了线性矩法的B值诺模图备用。This paper was focused on deriving the B nomogram of L-moments method, which was used to estimate the sampling errors in frequency analysis. The design floods are always added its mean square deviation to ensure the projects safety. An approximate formula of B based on Monte Carlo experiments, named B nomogram, is often used to estimate the mean square deviation. The L-moments method for flood frequency analysis is very efficient, which has some applications, but the B nomogram for L-moments method isn＇ t available now. Based on Monte Carlo experiments, the B nomogram of L-moments method has been developed and validated.

关 键 词：抽样误差 线性矩法 保证修正值系数 统计试验 

分 类 号：P333.6[天文地球—水文科学]