方法对比

	机器学习增强的反事实影响评估	反事实影响评估 (CIE)
领域	因果推断	因果推断
方法族	Regression model	Regression model
起源年份	2016-2019	1970s–2000s
提出者	Chernozhukov et al.; Athey & Imbens	Heckman, Imbens, Rubin, and the program evaluation literature
类型	Causal inference / ML-augmented evaluation	Causal inference / program evaluation
开创性文献	Chernozhukov, V., Chetverikov, D., Demirer, M., Duflo, E., Hansen, C., Newey, W., & Robins, J. (2018). Double/debiased machine learning for treatment and structural parameters. The Econometrics Journal, 21(1), C1-C68.	Heckman, J. J., & Vytlacil, E. J. (2007). Econometric evaluation of social programs, Part I: Causal models, structural models and econometric policy evaluation. Handbook of Econometrics, 6B, 4779-4874.
别名	ML-augmented counterfactual evaluation, ML-CIE, causal ML impact evaluation, double ML counterfactual evaluation	CIE, counterfactual evaluation, counterfactual policy evaluation, impact evaluation
相关	5	5
摘要	Machine learning-augmented counterfactual impact evaluation combines the credibility of potential-outcomes causal inference with the flexibility of modern ML algorithms. Rather than imposing parametric functional forms for confounders, ML learners — such as lasso, random forests, or neural nets — estimate nuisance functions (propensity scores, outcome regressions) that are then used to construct approximately unbiased estimates of causal effects. The canonical instantiation is Double/Debiased Machine Learning (DML), formalized by Chernozhukov et al. (2018).	Counterfactual Impact Evaluation is a family of causal methods that estimates the effect of an intervention by comparing what actually happened to participants with what would have happened had the intervention not taken place. Formalised in the Rubin Causal Model and extended by Heckman, Imbens and others, CIE underlies most modern program and policy evaluation practice.