Policymakers are required to evaluate the health benefits of reducing the National Ambient Air Quality Standards (NAAQS; i.e., the safety standards) for fine particulate matter PM 2.5 before implementing new policies. We formulate this objective as a shift-response function (SRF) and develop methods to analyze the problem using methods for causal inference, specifically under the stochastic interventions framework. SRFs model the average change in an outcome of interest resulting from a hypothetical shift in the observed exposure distribution. We propose a new broadly applicable doubly-robust method to learn SRFs using targeted regularization with neural networks. We evaluate our proposed method under various benchmarks specific for marginal estimates as a function of continuous exposure. Finally, we implement our estimator in the motivating application that considers the potential reduction in deaths from lowering the NAAQS from the current level of 12 $\mu g/m^3$ to levels that are recently proposed by the Environmental Protection Agency in the US (10, 9, and 8 $\mu g/m^3$).

翻译：摘要：政策制定者在实施新政策前，需评估降低国家环境空气质量标准（NAAQS，即安全标准）中细颗粒物PM2.5浓度所带来的健康效益。我们将此目标形式化为偏移响应函数（SRF），并利用因果推断方法（特别是随机干预框架）开发问题分析方法。SRF用于建模因观测暴露分布假设性偏移导致的目标结局平均变化。我们提出一种广泛适用的新双重稳健方法，通过神经网络的目标正则化学习SRF。在针对连续暴露边际估计的多种基准条件下评估所提方法。最后，我们在实际应用场景中实现估计量，考察将NAAQS从当前12 $\mu g/m^3$降至美国环境保护署近期提议的浓度水平（10、9和8 $\mu g/m^3$）可减少的潜在死亡人数。