Learning Adjustment Sets from Observational and Limited Experimental Data
Sofia Triantafillou, Gregory F. Cooper. Learning Adjustment Sets from Observational and Limited Experimental Data. 2020 . arXiv preprint arXiv:2005.08749, 2020
Estimating causal effects from observational data is not always possible due to confounding. Identifying a set of appropriate covariates (adjustment set) and adjusting for their inﬂuence can remove confounding bias; however, such a set is typically not identiﬁable from observational data alone. Experimental data do not have confounding bias, but are typically limited in sample size and can therefore yield imprecise estimates. Furthermore, experimental data often include a limited set of covariates, and therefore provide limited insight into the causal structure of the underlying system. In this work we introduce a method that combines large observational and limited experimentaldatatoidentifyadjustmentsetsandimprove the estimation of causal effects. The method identiﬁes an adjustment set (if possible) by calculating the marginal likelihood for the experimental data given observationallyderived prior probabilities of potential adjustmen sets. In this way, the method can make inferences that are not possible using only the conditional dependencies and independencies in all the observational and experimental data. We show that the method successfully identiﬁesadjustmentsetsandimprovescausaleffect estimation in simulated data, and it can sometimes make additional inferences when compared to state-of-the-art methods for combining experimental and observational data.