Consistent estimation of linear regression models using matched data
Consistent estimation of linear regression models using matched data
复制标题
DOI：
10.1016/j.jeconom.2017.07.006
复制
发表时间：
2018-04
影响因子：
6.3
通讯作者：
Masayuki Hirukawa;Artem Prokhorov
中科院分区：
文献类型：
--
作者：
Masayuki Hirukawa;Artem Prokhorov
经济学家经常使用匹配样本，尤其是在处理需要估算大量缺失观察值的收益数据时。在本文中，我们证明了使用匹配样本的线性回归模型的普通最小二乘估计量是不一致的，并且对于其概率极限具有非标准收敛速度。如果仅使用几个变量来估算缺失的数据，则可以纠正偏差。我们提出了两个半参数偏差校正估计量并探讨了它们的渐近性质。估计器具有间接推理解释，并且当匹配变量的数量不大于四个时，它们获得参数收敛率。蒙特卡罗模拟证实偏差校正在这种情况下效果非常好。
Economists often use matched samples, especially when dealing with earnings data where a number of missing observations need to be imputed. In this paper, we demonstrate that the ordinary least squares estimator of the linear regression model using matched samples is inconsistent and has a non-standard convergence rate to its probability limit. If only a few variables are used to impute the missing data, then it is possible to correct for the bias. We propose two semiparametric bias-corrected estimators and explore their asymptotic properties. The estimators have an indirect-inference interpretation, and they attain the parametric convergence rate when the number of matching variables is no greater than four. Monte Carlo simulations confirm that the bias correction works very well in such cases.