摘要
非参数核密度估计,核函数的选择并不唯一。在大样本情况下,通过理论证明了核函数在密度估计上具有渐近无偏性,相合性。借助软件R就常见的几种核函数通过实例说明,当带宽是最优选择时,核密度估计对核函数的选择并不敏感,采用不同核函数所得到的核密度估计差异不明显。
For nonparametric kernel density estimation, the choice of kernel function is not unique. In the case of large samples, the asymptotic unbiasedness and consistency of the kernel function in density estimation are proved theoretically. With the help of software R, several common kernels are illustrated by examples. When bandwidth is the best choice, the kernel density estimation is not sensitive to the choice of the kernels, and the difference of the kernels density estimation obtained by using different kernels is not obvious.
作者
唐兴芸
罗明燕
TANG Xing-yun;LUO Ming-yan(School of Mathematics and Statistics,Qiannan Normal University for Nationalities,Duyun 558000,Guizhou,China)
出处
《黔南民族师范学院学报》
2019年第4期10-13,共4页
Journal of Qiannan Normal University for Nationalities
关键词
核函数
核密度估计
带宽
kernel function
kernel density estimation
bandwidth
