ρ-混合下回归函数改良核估计的渐近正态性

Asymptotic normality of the improved Kernel estimator for regression function under ρ-mixing samples

利用混合序列基本不等式,把φ-混合样本下回归函数改良核估计的渐近正态推广到了ρ-混合样本情形.所得结果对条件的要求要比φ-混合样本情形的弱.

Using the elementary inequality of mixing sequence, promoted the asymptotic normality of the improved Kernel regression function estimate from φ-mixing samples to ρ-mixing samples. And the restrictions on conditions of ρ-mixing samples is less than that of φ-mixing samples.