arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2207.03035stat.MEecon.EMstat.ML
收藏

关于存在许多弱且无效工具变量时的工具变量估计

On the instrumental variable estimation with many weak and invalid instruments

Yiqi Lin, Frank Windmeijer, Xinyuan Song, Qingliang Fan

AI总结:

本文研究工具变量有效性未知时的线性IV模型识别问题,提出与最稀疏识别条件相一致的替代惩罚估计方法,在更弱的工具变量强度条件下证明了其理论优势,并通过模拟和BMI对舒张压影响的实证研究验证了方法性能。

摘要:

我们讨论线性工具变量(IV)模型中工具变量有效性未知这一根本性识别问题。在“最稀疏规则”假设下——该假设等价于多数规则,但在计算算法中具有可操作性——我们从选择一致性和对个体弱工具变量的容纳能力两方面,研究并证明了非凸惩罚方法相对于基于两步选择的其他工具变量估计量的优势。此外,我们提出了一种替代最稀疏惩罚,它与识别条件相一致,并同时提供oracle稀疏结构。与以往文献相比,所提出的估计量在更弱的工具变量强度条件下获得了理想的理论性质。通过模拟展示了有限样本性质,并将选择与估计方法应用于一项关于BMI对舒张压影响的实证研究。

英文摘要:

We discuss the fundamental issue of identification in linear instrumental variable (IV) models with unknown IV validity. With the assumption of the "sparsest rule", which is equivalent to the plurality rule but becomes operational in computation algorithms, we investigate and prove the advantages of non-convex penalized approaches over other IV estimators based on two-step selections, in terms of selection consistency and accommodation for individually weak IVs. Furthermore, we propose a surrogate sparsest penalty that aligns with the identification condition and provides oracle sparse structure simultaneously. Desirable theoretical properties are derived for the proposed estimator with weaker IV strength conditions compared to the previous literature. Finite sample properties are demonstrated using simulations and the selection and estimation method is applied to an empirical study concerning the effect of BMI on diastolic blood pressure.

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。

↑