Many causal inference approaches have focused on identifying an individual's outcome change due to a potential treatment, or the individual treatment effect (ITE), from observational studies. Rather than only estimating the ITE, we propose Collaborating Causal Networks (CCN) to estimate the full potential outcome distributions. This modification facilitates estimating the utility of each treatment and allows for individual variation in utility functions (e.g., variability in risk tolerance). We show that CCN learns distributions that asymptotically capture the correct potential outcome distributions under standard causal inference assumptions. Furthermore, we develop a new adjustment approach that is empirically effective in alleviating sample imbalance between treatment groups in observational studies. We evaluate CCN by extensive empirical experiments and demonstrate improved distribution estimates compared to existing Bayesian and Generative Adversarial Network-based methods. Additionally, CCN empirically improves decisions over a variety of utility functions.
翻译:许多因果推断方法侧重于确定个人因潜在治疗或个人治疗效果(ITE)而导致的结果变化,这些变化来自观察研究。我们提议,合作因果网络(CCN)不是仅仅估计ITE,而是建议合作因果网络(CCN)来估计全部潜在结果分布。这一修改有助于估计每种治疗的效用,并允许使用功能的个别变化(例如风险容忍度的变异性)。我们表明,CCN学会的分布在标准因果推断假设中,不时地捕捉正确的潜在结果分布。此外,我们制定了一种新的调整方法,在减轻观察研究中治疗组之间的抽样不平衡方面具有经验上的效力。我们通过广泛的实验性实验对CCN进行评价,并表明与现有的Bayesian和Generative Adversarial网络方法相比,分配估计数有所改善。此外,CCN从经验上改进了关于各种效用功能的决定。