Correcting the Factor Mirage: A Research Protocol for Causal Factor Investing
证明因子模型中的规范错误（如过度控制碰撞变量）会导致策略表现不佳甚至系统性损失，提出基于因果推断的计量规范调整，对因子投资从业者和研究者有警示意义。
In factor investing, <italic>p</italic>-hacking is a well-understood cause of false positives. A far less studied cause is factor model specification choices encouraged by the current econometric canon. We prove that specification errors can cause factor strategies to underperform and potentially yield systematic losses, even if <italic>all</italic> risk premia remain constant and are estimated with the correct sign. Unlike the <italic>p</italic>-hacking–driven factor zoo, where noise is mistaken for signal through repeated testing, we identify a distinct phenomenon—the factor mirage—in which canonical econometric practices systematically reward misspecified models that appear statistically strong but are structurally flawed. We show that these practices, especially overcontrolling for colliders, increase the likelihood of few-shot <italic>p</italic>-hacking and adverse outcomes. The implication is that specification errors are a more insidious and underappreciated threat to investors than previously recognized. To our knowledge, this is the first study to connect factor model selection, collider bias, underperformance, and systematic losses through a unified causal framework. These findings challenge the scientific credibility and long-term viability of the current associational (noncausal) multi-trillion-dollar factor investing industry. To address these risks, we propose adjustments to the econometric canon, informed by recent advances in machine learning and causal inference.