提出无需对照组的连续处理因果推断方法，量化宏观经济压力测试中的混杂偏误。
How Wrong Can Your Counterfactual Be? Quantifying Confounding Bias for Continuous Treatments without a Control Group
- 基于可解释敏感性参数构建混杂偏误闭式包络，适用于无对照组的面板数据。
- 实验证明传统预测模型因果偏差大且覆盖不足，新方法在各压力周期实现近名义覆盖率。
- 适合金融风控、政策评估等需评估反事实影响的场景，尤其当无法设置对照组时。
压力测试提出一个因果问题：若宏观经济走向不利的反事实路径，投资组合信用损失将如何变化？然而当前主流方法仍以预测为主，可能受遗漏变量偏误影响。本文针对具有连续共同处理变量且无对照组的面板数据，提出一种部分识别框架用于因果压力测试。通过假设未观测混杂因子对结果与宏观变量呈加性影响，推导出由两个可解释敏感性参数参数化的闭式混杂包络。进一步分析两种实用估计器——递归滚动与直接多步预测，推导非渐近误差界，并刻画递归累积何时使直接估计更优。推断方面，将识别包络与重要性加权的分位数预测结合，生成有限样本区间，可分离估计不确定性与识别不确定性，适用于协变量偏移情形。基于真实美国失业率路径构建的半合成实验表明，标准高精度预测模型仍存在显著因果偏差且覆盖严重不足，而所提框架在各压力周期均实现近名义覆盖率。
原文摘要 · Abstract (English)
Stress testing poses a causal question: how would portfolio credit losses change if the macroeconomy followed an adverse counterfactual path? Yet standard practice remains predictive and might be therefore vulnerable to omitted-variable bias. We propose a partial identification framework for causal stress testing in panel data with a continuous common treatment and no control group. By assuming that the unobserved confounder affects outcome and macro variables additively, we derive a closed-form confounding envelope parameterized by two interpretable sensitivity parameters. We further analyze two practical estimators -- recursive rollout and direct multi-horizon prediction -- derive non-asymptotic error bounds, and characterize when recursive compounding makes direct estimation preferable. For inference, we combine the identification envelope with importance-weighted conformal prediction, yielding finite-sample intervals that separate estimation uncertainty from identification uncertainty under covariate shift. In semi-synthetic experiments built from real U.S. unemployment paths, standard high-accuracy predictive models remain causally biased and substantially under-cover, whereas the proposed framework achieves near-nominal coverage across stress horizons.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。