Characterization of Overlap in Observational Studies
Characterization of Overlap in Observational Studies
复制标题
观察研究中重叠的特征
DOI：
--
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Kush R. Varshney
中科院分区：
文献类型：
--
作者：
Fredrik D. Johansson;Dennis Wei;Michael Oberst;Tian Gao;G. Brat;D. Sontag;Kush R. Varshney
治疗组之间需要重叠，以进行因果效应的非参数估计。如果一个受试者亚组总是接受相同的干预，那么在没有进一步假设的情况下，我们无法估计干预变化对该亚组的影响。当重叠不具有全局性时，表征重叠的局部区域可以告知新受试者因果结论的相关性，并可以帮助指导额外的数据收集。为了产生影响，这些描述必须对不是机器学习专家的下游用户（如政策制定者）具有可解释性。我们形式化重叠估计的问题，找到最小体积集的覆盖范围的限制，并减少这个问题的二元分类与布尔规则分类。然后，我们推广这种方法来估计重叠的政策评估。在几个实际应用中，我们证明了这些规则具有与黑盒估计相当的准确性，并提供了直观和翔实的解释，可以为政策制定提供信息。
Overlap between treatment groups is required for non-parametric estimation of causal effects. If a subgroup of subjects always receives the same intervention, we cannot estimate the effect of intervention changes on that subgroup without further assumptions. When overlap does not hold globally, characterizing local regions of overlap can inform the relevance of causal conclusions for new subjects, and can help guide additional data collection. To have impact, these descriptions must be interpretable for downstream users who are not machine learning experts, such as policy makers. We formalize overlap estimation as a problem of finding minimum volume sets subject to coverage constraints and reduce this problem to binary classification with Boolean rule classifiers. We then generalize this method to estimate overlap in off-policy policy evaluation. In several real-world applications, we demonstrate that these rules have comparable accuracy to black-box estimators and provide intuitive and informative explanations that can inform policy making.
DOI：
--
发表时间：
2018
期刊：
Proceedings of the 21st International Conference on Artificial Intelligence and Statistics (AISTATS
影响因子：
--
作者：
Kallus, Nathan;Zhou, Angela
通讯作者：
Zhou, Angela
影响因子：
6.3
作者：
D'Amour, Alexander;Ding, Peng;Sekhon, Jasjeet
通讯作者：
Sekhon, Jasjeet