Evaluating treatment effect heterogeneity widely informs treatment decision making. At the moment, much emphasis is placed on the estimation of the conditional average treatment effect via flexible machine learning algorithms. While these methods enjoy some theoretical appeal in terms of consistency and convergence rates, they generally perform poorly in terms of uncertainty quantification. This is troubling since assessing risk is crucial for reliable decision-making in sensitive and uncertain environments. In this work, we propose a conformal inference-based approach that can produce reliable interval estimates for counterfactuals and individual treatment effects under the potential outcome framework. For completely randomized or stratified randomized experiments with perfect compliance, the intervals have guaranteed average coverage in finite samples regardless of the unknown data generating mechanism. For randomized experiments with ignorable compliance and general observational studies obeying the strong ignorability assumption, the intervals satisfy a doubly robust property which states the following: the average coverage is approximately controlled if either the propensity score or the conditional quantiles of potential outcomes can be estimated accurately. Numerical studies on both synthetic and real datasets empirically demonstrate that existing methods suffer from a significant coverage deficit even in simple models. In contrast, our methods achieve the desired coverage with reasonably short intervals.
NCoRE: Neural Counterfactual Representation Learning for Combinations of Treatments
John A. Paulson School of Engineering and Applied Sciences, Harvard University（哈佛大学约翰·A·保尔森工程与应用科学学院）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；GlaxoSmithKline（葛兰素史克）
Sinkhorn Treatment Effects: A Causal Optimal Transport Measure
Department of Statistics, University of Washington, Seattle, WA, USA（华盛顿大学统计学系）；Department of Health Care Policy, Harvard Medical School, Boston, MA, USA（哈佛医学院医疗政策系）
Estimating counterfactual treatment outcomes over time in complex multiagent scenarios
Graduate School of Informatics at Nagoya University（名古屋大学信息学研究科）；RIKEN Center for Advanced Intelligence Project（理化学研究所先进智能项目中心）；Graduate School of Informatics at Kyoto University（京都大学信息学研究科）；Graduate School of Engineering at the University of Tokyo（东京大学工学研究科）；Graduate School of Information Science and Technology at Osaka University（大阪大学信息科学与技术研究科）
Counterfactual Uncertainty Quantification of Factual Estimand of Efficacy from Before-and-After Treatment Repeated Measures Randomized Controlled Trials
Department of Mathematics, The University of Manchester；Janssen Research；Pfizer Worldwide Research \& Development；Department of Statistics, The Ohio State University
Generalized Encouragement-Based Instrumental Variables for Counterfactual Regression
College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；Emory University（埃默里大学）；Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学高瓴人工智能学院）；Carnegie Mellon University（卡内基梅隆大学）
Proximal Causal Inference for Marginal Counterfactual Survival Curves
对比治疗组间的边缘反事实生存曲线是推断干预对右删失至事件时间结局的因果影响的有效且流行的方法。在观察环境中得出此类推论的一个关键挑战是可能存在未测量的混杂，这可能使假设没有隐藏混杂偏倚的最常用方法无效。在本文中，我们没有做出标准的无不可测量混杂假设，而是扩展了Miao et al.（2018），Tchetgen et al.（2020），Cui et al.（2020）最近提出的近端因果推断框架，以通过利用观察到的协变量作为不可测量混杂因素的不完美代理来获得因果生存对比的非参数识别。具体来说，我们开发了一个近端逆概率加权（PIPW）估计，标准IPW的近端模拟，它允许观察到的数据分布的时间到事件的结果，以保持完全不受限制。PIPW估计依赖于所谓的治疗混杂桥接函数的参数模型，该桥接函数将治疗过程与混杂代理相关联。因此，PIPW可能对模型错误指定敏感。为了提高稳健性和效率，我们还提出了一个近似双稳健估计，并建立了一致相合性和渐近正态性的估计。我们进行了广泛的模拟，以检查我们的估计有限样本的性能，并提出的方法应用于一项研究，评估重症监护室的重症患者的右心导管插入术的有效性。
Counterfactual inference in sequential experiments
Department of Operations Research and Information Engineering, Cornell Tech（Cornell Tech 运营研究与信息工程系）；Department of Statistics, Harvard University（哈佛大学统计学系）；School of Information, University of Michigan（密歇根大学信息学院）；Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology（麻省理工学院电气工程与计算机科学系）
Generative Flows for Potential Outcomes and Counterfactuals
School of Industrial and Systems Engineering（工业与系统工程学院）；Georgia Institute of Technology（佐治亚理工学院）；Elmore Family School of Electrical and Computer Engineering（埃洛姆家族电气与计算机工程学院）；Purdue University（普渡大学）
DR-VIDAL -- Doubly Robust Variational Information-theoretic Deep Adversarial Learning for Counterfactual Prediction and Treatment Effect Estimation on Real World Data
University of Pittsburgh（匹兹堡大学）；University of Florida（佛罗里达大学）
Do We Exploit all Information for Counterfactual Analysis? Benefits of Factor Models and Idiosyncratic Correction
Princeton University（普林斯顿大学）；Sao Paulo School of Economics (EESP), Getulio Vargas Foundation（圣保罗经济学院，热图利奥·瓦加斯基金会）；Pontifical Catholic University of Rio de Janeiro (PUC-Rio)（里约热内卢天主教大学）
最优定价，即，确定使给定产品的利润或收入最大化的价格水平是零售业的重要任务。要选择这样一个数量，首先需要从产品需求中估计价格弹性。回归方法通常无法恢复这种弹性，由于混杂效应和价格的内生性。因此，通常需要随机化实验。然而，弹性可以是高度异质性的，这取决于例如商店的位置。由于随机化经常发生在市政一级，标准的差异中的差异方法也可能失败。可能的解决方案是基于方法来测量处理对单个（或仅仅几个）处理单元的影响，该方法基于从人工控制构建的反事实。例如，对于处理组中的每个城市，可以从未处理的位置构建反事实。在本文中，我们采用了一种新的高维统计方法来衡量价格变化对巴西一家主要零售商的日常销售额的影响。所提出的方法结合了主成分（因子）和稀疏回归，从而产生了一种称为因子调整正则化治疗评价方法（\texttt{FarmTreat}）的方法。这些数据包括400多个城市的五种不同产品的每日销售和价格。所考虑的产品属于\emph{sweet and candies}类别，并已在2016年和2017年进行了实验。我们的研究结果证实了假设的高度异质性产生非常不同的定价策略，在不同的城市。
