This paper studies the small sample properties and bias of just-identified instrumental variable quantile regression (IVQR) estimators, nesting order statistics and classical quantile regression. We propose a theoretical framework for analyzing small sample properties based on a novel approximation of the discontinuous sample moments with a H\"older continuous process. Using this approximation, we derive remainder bounds with nearly-optimal rates for the asymptotic linear expansions of exact and k-step estimators of IVQR models. Furthermore, we derive a bias formula for exact IVQR estimators up to order $O\left(\frac{1}{n}\right)$. The bias contains components that cannot be consistently estimated and depend on the particular numerical estimation algorithm. To circumvent this problem, we propose a novel 1-step adjustment of the estimator, which admits a feasible bias correction. We suggest using bias-corrected exact estimators, when possible, to achieve the smallest bias. Otherwise, applying 1-step corrections may improve the higher-order bias and MSE of any consistent estimator.
翻译:本文研究简单识别的可变微量回归(IVQR) 估计器的微小样本属性和偏差、 嵌套顺序统计和典型微量回归的偏差。 我们提出一个理论框架来分析小样本属性, 以H\'older 连续过程的不连续抽样时刻的新近似值为基础。 使用这个近似值, 我们从剩余值中得出近乎最佳的误差, 用于精确和k- step 估测器的静态线性扩展。 此外, 我们为确切的 IVQR 估计器得出一个偏差公式, 最高可订购 $O\left( frac{1 ⁇ n ⁇ n ⁇ right) 。 偏差包含无法持续估算且取决于特定数字估算算法的组件。 为避免这一问题, 我们提议对估计器的偏差值进行新的一步调整, 并承认可能的偏差修正。 我们建议尽可能使用偏差精确的估测算器来达到最小的偏差。 否则, 采用一步校正的校正可以改进任何一致估测器的偏差性。 。 否则, 。