ASYMPTOTIC NORMALITY OF A NONPARAMETRIC INSTRUMENTAL VARIABLES ESTIMATOR*
给出了Hall和Horowitz非参数工具变量估计量渐近正态分布的条件，并可用大样本构造置信区间，通过蒙特卡洛模拟检验了有限样本覆盖概率。
This article gives conditions under which the nonparametric instrumental variables estimator of Hall and Horowitz ( Annals of Statistics 33 (December 2005), 2904–2929) is asymptotically normally distributed. With sufficiently large samples, the asymptotic normality result can be used to form confidence intervals for the unknown function that is estimated by the Hall–Horowitz procedure. The article reports the results of a Monte Carlo investigation of the finite‐sample coverage probabilities of the confidence intervals.