There are many scenarios where short- and long-term causal effects of an intervention are different. For example, low-quality ads may increase short-term ad clicks but decrease the long-term revenue via reduced clicks. This work, therefore, studies the problem of long-term effect where the outcome of primary interest, or primary outcome, takes months or even years to accumulate. The observational study of long-term effect presents unique challenges. First, the confounding bias causes large estimation error and variance, which can further accumulate towards the prediction of primary outcomes. Second, short-term outcomes are often directly used as the proxy of the primary outcome, i.e., the surrogate. Nevertheless, this method entails the strong surrogacy assumption that is often impractical. To tackle these challenges, we propose to build connections between long-term causal inference and sequential models in machine learning. This enables us to learn surrogate representations that account for the temporal unconfoundedness and circumvent the stringent surrogacy assumption by conditioning on the inferred time-varying confounders. Experimental results show that the proposed framework outperforms the state-of-the-art.
Evaluating for the long term: Learnings from industry
Pinterest；METR；Netflix；MIT CSAIL（麻省理工学院计算机科学与人工智能实验室）；UC Berkeley CHAI（加州大学伯克利分校人类中心人工智能研究所）；Airbnb；Meta；Statsig；Uber；Cornell University（康奈尔大学）；Harvard Business School（哈佛商学院）；Lyft；Datadog；Google；Knight-Georgetown Institute（Knight-乔治城研究所）；University of Chicago Booth School of Business（芝加哥大学布斯商学院）；Roblox；MIT（麻省理工学院）
当主要结局难以收集时，通常使用替代终点作为替代。有可能对于每个个体，治疗对替代物有积极影响，替代物对主要结局有积极影响，但对于某些个体，治疗对主要结局有负面影响。例如，治疗可能在预防每个人的中风方面基本上是有效的，并且降低中风的风险对于更长的生存时间是普遍有益的，然而，治疗仍然可能导致一些个体的死亡。我们将这种悖论现象称为个体替代悖论。个体替代悖论是为了捕捉处理效应异质性而提出的，这是基于平均因果效应（ACE）的替代悖论无法描述的（Chen et al.，2007）或基于分布因果效应（DCE）（Ju和Geng，2010）。我们调查现有的替代标准的个人替代悖论是否会出现。我们发现，只有强二元替代可以避免这种悖论，而无需额外的假设。利用这个锐界，我们提出了排除个体代理悖论的新准则。我们的方法在应用程序中说明，以确定对糖尿病视网膜病变的发展或进展的风险的影响，密集的视网膜病变。
Double/debiased machine learning of quantile treatment effects on long-term outcomes in clinical trials
Faculty of Arts and Sciences, Beijing Normal University（北京师范大学文理学院）；School of Mathematics and Statistics, Beijing Technology and Business University（北京工商大学数学与统计学院）；School of Statistics, Beijing Normal University（北京师范大学统计学院）
Comparison of Polynomial Chaos and Gaussian Process surrogates for uncertainty quantification and correlation estimation of spatially distributed open-channel steady flows
Efficient estimation of cumulative incidence curves via data fusion with surrogates: application to integrated analysis of vaccine trial and immunobridging data
University of Cambridge（剑桥大学）；Fred Hutchinson Cancer Center（弗雷德·哈钦森癌症中心）；Ghent University（根特大学）
Quantifying the Uncertainty in Model Parameters Using Gaussian Process-Based Markov Chain Monte Carlo: An Application to Cardiac Electrophysiological Models
Rochester Institute of Technology（罗切斯特理工学院）；Dalhousie University（达尔豪斯大学）
