因果推理
灵敏度(控制系统)
频数推理
推论
计量经济学
计算机科学
非参数统计
贝叶斯概率
可见的
缺少数据
因式分解
观察研究
分位数
启发式
贝叶斯推理
数据挖掘
机器学习
数学
统计
人工智能
算法
数学优化
工程类
物理
量子力学
电子工程
作者
Alexander Franks,Alexander D’Amour,Avi Feller
标识
DOI:10.1080/01621459.2019.1604369
摘要
Abstract A fundamental challenge in observational causal inference is that assumptions about unconfoundedness are not testable from data. Assessing sensitivity to such assumptions is therefore important in practice. Unfortunately, some existing sensitivity analysis approaches inadvertently impose restrictions that are at odds with modern causal inference methods, which emphasize flexible models for observed data. To address this issue, we propose a framework that allows (1) flexible models for the observed data and (2) clean separation of the identified and unidentified parts of the sensitivity model. Our framework extends an approach from the missing data literature, known as Tukey's factorization, to the causal inference setting. Under this factorization, we can represent the distributions of unobserved potential outcomes in terms of unidentified selection functions that posit a relationship between treatment assignment and unobserved potential outcomes. The sensitivity parameters in this framework are easily interpreted, and we provide heuristics for calibrating these parameters against observable quantities. We demonstrate the flexibility of this approach in two examples, where we estimate both average treatment effects and quantile treatment effects using Bayesian nonparametric models for the observed data.
科研通智能强力驱动
Strongly Powered by AbleSci AI