Estimation of causal effects using machine learning methods has become an active research field in econometrics. In this paper, we study the finite sample performance of meta-learners for estimation of heterogeneous treatment effects under the usage of sample-splitting and cross-fitting to reduce the overfitting bias. In both synthetic and semi-synthetic simulations we find that the performance of the meta-learners in finite samples greatly depends on the estimation procedure. The results imply that sample-splitting and cross-fitting are beneficial in large samples for bias reduction and efficiency of the meta-learners, respectively, whereas full-sample estimation is preferable in small samples. Furthermore, we derive practical recommendations for application of specific meta-learners in empirical studies depending on particular data characteristics such as treatment shares and sample size.
B-Learner: Quasi-Oracle Bounds on Heterogeneous Causal Effects Under Hidden Confounding
Cornell University（康奈尔大学）；Cornell Tech（康奈尔科技校区）；Princeton University（普林斯顿大学）；Technion, Israel Institute of Technology（以色列理工学院）；University of Oxford（牛津大学）
Stanford University（斯坦福大学）；Microsoft Research（微软研究院）；U.S. Bureau of Economic Analysis（美国经济分析局）
Estimating heterogeneous treatment effects in domains such as healthcare or social science often involves sensitive data where protecting privacy is important. We introduce a general meta-algorithm for estimating conditional average treatment effects (CATE) with differential privacy (DP) guarantees. Our meta-algorithm can work with simple, single-stage CATE estimators such as S-learner and more complex multi-stage estimators such as DR and R-learner. We perform a tight privacy analysis by taking advantage of sample splitting in our meta-algorithm and the parallel composition property of differ…
The University of Tokyo（东京大学）；CyberAgent, Inc.（CyberAgent公司）
We study the benign overfitting theory in the prediction of the conditional average treatment effect (CATE), with linear regression models. As the development of machine learning for causal inference, a wide range of large-scale models for causality are gaining attention. One problem is that suspicions have been raised that the large-scale models are prone to overfitting to observations with sample selection, hence the large models may not be suitable for causal prediction. In this study, to resolve the suspicious, we investigate on the validity of causal inference methods for overparameterize…
Many causal and structural effects depend on regressions. Examples include policy effects, average derivatives, regression decompositions, average treatment effects, causal mediation, and parameters of economic structural models. The regressions may be high dimensional, making machine learning useful. Plugging machine learners into identifying equations can lead to poor inference due to bias from regularization and/or model selection. This paper gives automatic debiasing for linear and nonlinear functions of regressions. The debiasing is automatic in using Lasso and the function of interest wi…
There is growing interest in estimating and analyzing heterogeneous treatment effects in experimental and observational studies. We describe a number of meta-algorithms 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. Meta-algorithms build on base algorithms---such as Random Forests (RF), Bayesian Additive Regression Trees (BART) or neural networks---to estimate the CATE, a function that the base algorithms are not designed to estimate directly. We introduce a new met…
National University of Singapore（新加坡国立大学）；Tsinghua University（清华大学）；Renmin University of China（中国人民大学）；University of Science and Technology of China（中国科学技术大学）；Hefei Comprehensive National Science Center（合肥综合性国家科学中心）
Under stringent model type and variable distribution assumptions, differentiable score-based causal discovery methods learn a directed acyclic graph (DAG) from observational data by evaluating candidate graphs over an average score function. Despite great success in low-dimensional linear systems, it has been observed that these approaches overly exploit easier-to-fit samples, thus inevitably learning spurious edges. Worse still, inherent mostly in these methods the common homogeneity assumption can be easily violated, due to the widespread existence of heterogeneous data in the real world, re…
TTCD:Transformer Integrated Temporal Causal Discovery from Non-Stationary Time Series Data
Department of Information Systems（信息系统系）；University of Maryland, Baltimore County（马里兰大学巴尔的摩县分校）；Department of Data Science（数据科学系）；University of North Texas（北德克萨斯大学）；Climate Science Section（气候科学组）；Lawrence Livermore National Laboratory（劳伦斯利弗莫尔国家实验室）
Université de Montréal（蒙特利尔大学）；Ruprecht-Karls-Universität Heidelberg（海德堡大学）；École Polytechnique Montréal（蒙特利尔综合理工学院）
We propose to meta-learn causal structures based on how fast a learner adapts to new distributions arising from sparse distributional changes, e.g. due to interventions, actions of agents and other sources of non-stationarities. We show that under this assumption, the correct causal structural choices lead to faster adaptation to modified distributions because the changes are concentrated in one or just a few mechanisms when the learned knowledge is modularized appropriately. This leads to sparse expected gradients and a lower effective number of degrees of freedom needing to be relearned whil…
Conformal Convolution and Monte Carlo Meta-learners for Predictive Inference of Individual Treatment Effects
IDLab Department of Electronics and Information Systems Ghent University, Belgium（IDLab电子与信息系统系根特大学，比利时）；IDLab Department of Electronics and Information Systems Ghent University - imec, Belgium（IDLab电子与信息系统系根特大学-imec，比利时）；Biometrics Research Group Department of Morphology, Imaging, Orthopedics, Rehabilitation and Nutrition Ghent University, Belgium（生物医学研究组形态学、成像、骨科、康复与营养系根特大学，比利时）
University of Cambridge（剑桥大学）；UCLA（加州大学洛杉矶分校）；The Alan Turing Institute（艾伦图灵研究所）
Conditional average treatment effects (CATEs) allow us to understand the effect heterogeneity across a large population of individuals. However, typical CATE learners assume all confounding variables are measured in order for the CATE to be identifiable. This requirement can be satisfied by collecting many variables, at the expense of increased sample complexity for estimating CATEs. To combat this, we propose an energy-based model (EBM) that learns a low-dimensional representation of the variables by employing a noise contrastive loss function. With our EBM we introduce a preprocessing step t…
Hong Kong University of Science and Technology（香港科技大学）；New York University（纽约大学）；Spotify
This study presents a systematic comparison of methods for individual treatment assignment, a general problem that arises in many applications and has received significant attention from economists, computer scientists, and social scientists. We group the various methods proposed in the literature into three general classes of algorithms (or metalearners): learning models to predict outcomes (the O-learner), learning models to predict causal effects (the E-learner), and learning models to predict optimal treatment assignments (the A-learner). We compare the metalearners in terms of (1) their l…
Although review papers on causal inference methods are now available, there is a lack of introductory overviews on what they can render and on the guiding criteria for choosing one particular method. This tutorial gives an overview in situations where an exposure of interest is set at a chosen baseline (`point exposure') and the target outcome arises at a later time point. We first phrase relevant causal questions and make a case for being specific about the possible exposure levels involved and the populations for which the question is relevant. Using the potential outcomes framework, we desc…
We investigate the finite sample performance of sample splitting, cross-fitting and averaging for the estimation of the conditional average treatment effect. Recently proposed methods, so-called meta-learners, make use of machine learning to estimate different nuisance functions and hence allow for fewer restrictions on the underlying structure of the data. To limit a potential overfitting bias that may result when using machine learning methods, cross-fitting estimators have been proposed. This includes the splitting of the data in different folds to reduce bias and averaging over folds to re…
Complex distributions of the healthcare expenditure pose challenges to statistical modeling via a single model. Super learning, an ensemble method that combines a range of candidate models, is a promising alternative for cost estimation and has shown benefits over a single model. However, standard approaches to super learning may have poor performance in settings where extreme values are present, such as healthcare expenditure data. We propose a super learner based on the Huber loss, a "robust" loss function that combines squared error loss with absolute loss to down-weight the influence of ou…
Carnegie Mellon University（卡内基梅隆大学）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；University of California, San Diego（加利福尼亚大学圣迭戈分校）；Guangdong University of Technology（广东工业大学）；University of Melbourne（墨尔本大学）；Shiga University（滋贺大学）；RIKEN（理化学研究所）
Meta-analysis is commonly used to combine results from multiple clinical trials, but traditional meta-analysis methods do not refer explicitly to a population of individuals to whom the results apply and it is not clear how to use their results to assess a treatment's effect for a population of interest. We describe recently-introduced causally-interpretable meta-analysis methods and apply their treatment effect estimators to two individual-participant data sets. These estimators transport estimated treatment effects from studies in the meta-analysis to a specified target population using indi…
We propose a counterfactual approach to train ``causality-aware" predictive models that are able to leverage causal information in static anticausal machine learning tasks (i.e., prediction tasks where the outcome influences the features). In applications plagued by confounding, the approach can be used to generate predictions that are free from the influence of observed confounders. In applications involving observed mediators, the approach can be used to generate predictions that only capture the direct or the indirect causal influences. Mechanistically, we train supervised learners on (coun…
Curious Causality-Seeking Agents Learn Meta Causal World
University of Bristol（布里斯托大学）；Peking University（北京大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, Chinese Academy of Sciences（中国科学院人工智能学院）；University College London（伦敦大学学院）；King Abdullah University of Science and Technology（卡塔尔科技大学）；The Swiss AI Lab, IDSIA-USI/SUPSI（瑞士AI实验室，IDSIA-USI/SUPSI）
