The Normal Approximation for Semiparametric Averaged Derivatives
证明半参数平均导数估计的有限样本分布收敛到正态分布的速度可与标准参数统计量相当，对使用该方法的实证研究者有参考价值。
With the same normalization as that for standard parametric statistics, and centered at a parameter of interest, many semiparametric estimates based on n observations have been shown to be root-n-consistent and asymptotically normal. In the context of semiparametric averaged derivative estimates, we go further by showing that the rate of convergence of the finite-sample distribution to the normal limit distribution can equal that of standard parametric statistics.