论文标题
数据驱动的固定效果面板数据模型的强大估计方法
Data Driven Robust Estimation Methods for Fixed Effects Panel Data Models
论文作者
论文摘要
面板数据回归模型在不同的研究领域中引起了人们的关注，包括但不限于计量经济学，环境科学，流行病学，行为和社会科学。但是，在面板数据中存在外围观察结果通常会导致对模型参数的偏差和效率低下的估计，从而在应用最小二乘（LS）方法时会导致不可靠的推断。我们提出了M估计方法的扩展，并通过数据驱动的调谐参数选择，以实现对异常值的理想鲁棒性水平，而不会损失估计效率。在某些轻微的规律条件下，也证明了所提出的估计量的一致性和渐近正态性。已经通过广泛的仿真研究和宏观经济数据应用了现有和提出的强大估计器的有限样本特性。我们的发现表明，所提出的方法在存在异常值的情况下通常表现出改进的估计和预测性能，并且在没有污染时与传统的LS方法一致。
The panel data regression models have gained increasing attention in different areas of research including but not limited to econometrics, environmental sciences, epidemiology, behavioral and social sciences. However, the presence of outlying observations in panel data may often lead to biased and inefficient estimates of the model parameters resulting in unreliable inferences when the least squares (LS) method is applied. We propose extensions of the M-estimation approach with a data-driven selection of tuning parameters to achieve desirable level of robustness against outliers without loss of estimation efficiency. The consistency and asymptotic normality of the proposed estimators have also been proved under some mild regularity conditions. The finite sample properties of the existing and proposed robust estimators have been examined through an extensive simulation study and an application to macroeconomic data. Our findings reveal that the proposed methods often exhibits improved estimation and prediction performances in the presence of outliers and are consistent with the traditional LS method when there is no contamination.
