Основные понятия
本文闡述了殘差化方法在處理多元線性回歸模型中多重共線性問題的應用,並探討了其與 FWL 定理的關係,強調該方法不僅能減輕多重共線性,還能用於分析自變量對應變量的獨立影響。
Статистика
Diebold and Li (2006) 將 λ 值固定為 0.0609,這表明因子載荷之間僅存在微弱的正相關。
León et al. (2018) 將 λ 設定為 0.01,這導致短期和中期之間的相關係數等於 -0.9920。
Цитаты
"This paper aims to contribute to a better understanding of the residualization procedure to promote an adequate application and interpretation of it."
"In short, the FWL theorem establishes equivalences between the estimates of two different models, while residualization establishes the differences between two very similar models that are not exactly the same."