arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.00655econ.EM
收藏

局部投影与 VAR:来自数千个 DGP 的经验教训

Local Projections vs. VARs: Lessons From Thousands of DGPs

Dake Li, Mikkel Plagborg-Møller, Christian K. Wolf

AI总结:

本文通过覆盖数千个模拟美国宏观数据性质的 DGP,系统比较 LP 与 VAR 结构脉冲响应估计量,揭示偏差—方差权衡并给出依研究偏好选择方法的准则。

摘要:

我们对结构脉冲响应的 Local Projection(LP,局部投影)估计量与 Vector Autoregression(VAR,向量自回归)估计量开展了一项模拟研究,覆盖数千个数据生成过程(DGP),这些 DGP 旨在模拟美国宏观经济数据全集的性质。我们的分析考虑了多种识别方案以及 LP 和 VAR 估计量的若干变体,采用了偏差校正、收缩或模型平均。结果呈现出清晰的偏差—方差权衡:LP 估计量的偏差低于 VAR 估计量,但在中期和长期 horizons 上,其方差也显著更高。当且仅当研究者压倒性地优先考虑偏差时,偏差校正 LP 才是首选方法。对于同样重视精度的研究者,VAR 方法最具吸引力——短期和长期 horizons 使用 Bayesian VAR,而中期和长期 horizons 使用最小二乘 VAR。

英文摘要:

We conduct a simulation study of Local Projection (LP) and Vector Autoregression (VAR) estimators of structural impulse responses across thousands of data generating processes, designed to mimic the properties of the universe of U.S. macroeconomic data. Our analysis considers various identification schemes and several variants of LP and VAR estimators, employing bias correction, shrinkage, or model averaging. A clear bias-variance trade-off emerges: LP estimators have lower bias than VAR estimators, but they also have substantially higher variance at intermediate and long horizons. Bias-corrected LP is the preferred method if and only if the researcher overwhelmingly prioritizes bias. For researchers who also care about precision, VAR methods are the most attractive -- Bayesian VARs at short and long horizons, and least-squares VARs at intermediate and long horizons.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑