基于LENQD序列生成的线性过程误差回归函数小波估计Berry-Esseen界

Berry-Esseen Bound of Wavelet Estimator for Regression Model with Linear Process Errors Generated by LENQD Sequence

在LENQD相依序列生产的线性过程误差下,研究了固定设计非参数回归模型小波估计.利用LENQD序列的矩不等式和特征函数不等式,建立了未知回归函数小波估计的Berry-Esseen界.通过选取适当的参数,其界可达O(n^(−1/6)).所得结果推广了相关文献的研究结果.

Based on linear process random errors generated by LENQD random sequence,the wavelet estimator of nonparametric fixed design regression model is considered.By the characteristic function inequality and moment inequality of LENQD random sequence,the Berry-Esseen bounds of the wavelet estimator for unknown regression function are obtained.And by choosing some suitable constants,their bounds can reach O(n^(−1/6)).The obtained results generalize the corresponding results in recent literature.