Causal inference methods for treatment effect estimation usually assume independent units. However, this assumption is often questionable because units may interact, resulting in spillover effects between units. We develop augmented inverse probability weighting (AIPW) for estimation and inference of the direct effect of the treatment with observational data from a single (social) network with spillover effects. We use plugin machine learning and sample splitting to obtain a semiparametric treatment effect estimator that converges at the parametric rate and asymptotically follows a Gaussian distribution. We apply our AIPW method to the Swiss StudentLife Study data to investigate the effect of hours spent studying on exam performance accounting for the students' social network.

翻译：因果推断方法在治疗效果估计中通常假设各单元相互独立。然而，这一假设往往令人存疑，因为单元之间可能产生相互作用，导致跨单元溢出效应。我们提出了增强逆概率加权（AIPW）方法，用于从存在溢出效应的单一（社交）网络观测数据中估计和推断治疗的直接效应。我们利用插件式机器学习与样本分割技术，构建出一个以参数速率收敛且渐近服从高斯分布的半参数治疗效果估计量。我们将该AIPW方法应用于瑞士学生生活研究数据，探究在考虑学生社交网络影响的前提下，学习时长对考试成绩的作用。