Causal effect estimation is important for numerous tasks in the natural and social sciences. However, identifying effects is impossible from observational data without making strong, often untestable assumptions. We consider algorithms for the partial identification problem, bounding treatment effects from multivariate, continuous treatments over multiple possible causal models when unmeasured confounding makes identification impossible. We consider a framework where observable evidence is matched to the implications of constraints encoded in a causal model by norm-based criteria. This generalizes classical approaches based purely on generative models. Casting causal effects as objective functions in a constrained optimization problem, we combine flexible learning algorithms with Monte Carlo methods to implement a family of solutions under the name of stochastic causal programming. In particular, we present ways by which such constrained optimization problems can be parameterized without likelihood functions for the causal or the observed data model, reducing the computational and statistical complexity of the task.
翻译:对自然科学和社会科学的许多任务来说,因果关系估计很重要。然而,如果不作出强有力的、往往是无法检验的假设,观察数据就不可能产生确认效果。我们考虑部分识别问题的算法,将处理效果与多种可能的因果模型相捆绑,如果无法计量的混杂使得无法识别,则对多种可能的因果模型进行连续处理。我们考虑一个框架,使可观察证据与根据基于规范的标准将因果模型编码成的因果模型的影响相匹配。这概括了纯粹基于基因化模型的古典方法。在有限的优化问题中将因果效应作为客观功能,我们把灵活学习算法与蒙特卡洛方法结合起来,以随机随机随机性因果编程的名义实施一系列解决方案。特别是,我们提出了如何在不考虑因果或观察到的数据模型的可能性功能的情况下将这种受限优化问题参数化,从而减少任务的计算和统计复杂性。