关键词: 测度误差, 线性模型, 两步估计法, 工具变量法

Abstract: Measurement errors are pervasive in data sets. This paper proposes a two-step estimation approach for linear models with measurement errors, and argues that the approach can generate consistent and asymptotic normal estimators. The study derives more efficient and more robust estimators on top the baseline one, and applies the estimation to time series and panel data models. Comparison between the two-step estimation and instrumental variable estimation is exhibited under some assumption, and it shows that the former strictly dominates the latter. A Monte Carlo simulation corroborates the performance of the estimators in the case of finite sample, and demonstrates also the comparative advantage of two step estimation over its instrumental variable counterpart.

Key words: Measurement Error, Linear Model, Two Step Estimation, Instrumental Variable Estimation