Estimation of causal effects using linear non-Gaussian causal models with hidden variables
Estimation of causal effects using linear non-Gaussian causal models with hidden variables
复制标题
DOI：
10.1016/j.ijar.2008.02.006
复制
发表时间：
2008-10-01
影响因子：
3.9
通讯作者：
Palviainen, Markus
中科院分区：
文献类型：
--
作者：
Hoyer, Patrik O.;Shimizu, Shohei;Palviainen, Markus
从非实验数据中估计因果效应的任务是出了名的困难和不可靠。然而，在包括经济学和社会科学在内的许多领域，通常都需要准确的此类估计，而在这些领域，受控实验往往是不可能的。线性因果模型(结构方程模型)与数据的隐含正态(高斯)假设相结合，为这项任务提供了一个广泛使用的框架。我们最近描述了如何利用数据中的非高斯性来估计因果效应。在这篇文章中，我们证明，对于非高斯数据，即使在存在隐藏变量(未观察到的混杂因素)的情况下，即使这些变量的存在是先验未知的，因果推断也是可能的。因此，我们提供了一个全面而完整的框架，用于估计线性、非高斯域中观察变量之间的因果效应。数值仿真验证了所提方法的实际实现，并提供了所有仿真的完整的MatLab代码。(C)2008 Elsevier Inc.保留所有权利。
The task of estimating causal effects from non-experimental data is notoriously difficult and unreliable. Nevertheless, precisely such estimates are commonly required in many fields including economics and social science, where controlled experiments are often impossible. Linear causal models (structural equation models), combined with an implicit normality (Gaussianity) assumption on the data, provide a widely used framework for this task. We have recently described how non-Gaussianity in the data can be exploited for estimating causal effects. In this paper we show that, with non-Gaussian data, causal inference is possible even in the presence of hidden variables (unobserved confounders), even when the existence of such variables is unknown a priori. Thus, we provide a comprehensive and complete framework for the estimation of causal effects between the observed variables in the linear, non-Gaussian domain. Numerical simulations demonstrate the practical implementation of the proposed method, with full Matlab code available for all simulations. (C) 2008 Elsevier Inc. All rights reserved.