Metalearners for estimating heterogeneous treatment effects using machine learning
Metalearners for estimating heterogeneous treatment effects using machine learning
复制标题
DOI：
10.1073/pnas.1804597116
复制
发表时间：
2019-03-05
影响因子：
11.1
通讯作者：
Yu, Bin
中科院分区：
文献类型：
--
作者：
Kunzel, Soren R.;Sekhon, Jasjeet S.;Yu, Bin
在实验性和观察性研究中，对异质性治疗效果的估计和分析越来越受到关注。我们描述了一些元算法，这些元算法可以利用机器学习和统计学中的任何监督学习或回归方法来估计条件平均治疗效果（CATE）函数。元算法建立在基础算法上，如随机森林（RF），贝叶斯加性回归树（BART）或神经网络，以估计CATE，基础算法不是直接估计的函数。我们介绍了一种元算法，X-学习者，这是证明有效的单位在一个治疗组的数量远远大于其他，可以利用CATE功能的结构特性时。例如，如果CATE函数是线性的，并且治疗和控制中的响应函数是Lipschitz连续的，则X学习器仍然可以在规则性条件下实现参数速率。然后，我们介绍使用RF和BART作为基础学习器的X-learner版本。在广泛的模拟研究中，X学习者表现良好，尽管没有一个元学习者是最好的。在政治学的两个说服领域的实验中，我们展示了我们的X-学习者如何可以用于目标治疗制度，并揭示了潜在的机制。提供了实现我们的方法的软件包。
There is growing interest in estimating and analyzing heterogeneous treatment effects in experimental and observational studies. We describe a number of metaalgorithms that can take advantage of any supervised learning or regression method in machine learning and statistics to estimate the conditional average treatment effect (CATE) function. Metaalgorithms build on base algorithms-such as random forests (RFs), Bayesian additive regression trees (BARTs), or neural networks-to estimate the CATE, a function that the base algorithms are not designed to estimate directly. We introduce a metaalgorithm, the X-learner, that is provably efficient when the number of units in one treatment group is much larger than in the other and can exploit structural properties of the CATE function. For example, if the CATE function is linear and the response functions in treatment and control are Lipschitz-continuous, the X-learner can still achieve the parametric rate under regularity conditions. We then introduce versions of the X-learner that use RF and BART as base learners. In extensive simulation studies, the X-learner performs favorably, although none of the metalearners is uniformly the best. In two persuasion field experiments from political science, we demonstrate how our X-learner can be used to target treatment regimes and to shed light on underlying mechanisms. A software package is provided that implements our methods.