The subroutines glkern.f and lokern.f use an efficient and fast algorithm for automatically adaptive nonparametric regression estimation with a kernel method. Roughly speaking, the method performs a local averaging of the observations when es

kernel density estimation based on fast marching method

用5种非参数方法：线性样条、B样条、N-W核估计、最近邻估计、局部多项式对某地SO2浓度数据进行拟合。(5 non parametric methods: linear spline, B spline, N-W kernel estimation, nearest neighbor estimation, and local polynomial are used to fit the SO2 concentration data in a certain area.)