|
福州大学学报(自然科学版) 2018
基于Bootstrap思想的非参数检验p值的估计方法
|
Abstract:
在总体分布未知且样本量较小时,基于Bootstrap思想和随机模拟方法,讨论了非参数检验的三种方法及其检验p值的估计,并通过R程序加以实现. 最后以已知分布的随机样本构建某些统计量为例作模拟实验,给出三种估计方法与常规方法的比较.
Based on the Bootstrap idea and the method of stochastic simulation,this paper discussed three estimation methods of nonparametric test and its’ p value calculation when the population (distribution) is unknown and the sample size is small. It also put forward the realization programs by R software. At the end,it took some random samples with known distribution as the sources of simulation to compare the above methods with general methods