Estimating Population Average Causal Effects in the Presence of Non-Overlap: A Bayesian Approach
share
Most causal inference studies rely on the assumption of positivity, or overlap, to identify population or sample average causal effects. When this assumption is violated, these estimands are unidentifiable without some degree of reliance on model specifications, due to poor data support. Existing methods to address non-overlap, such as trimming or down-weighting data in regions of poor support, all suffer from the limitation of changing the estimand. The change in estimand may diminish the impact of the study results, particularly for studies intended to influence policy, because estimates may not be representative of effects in the population of interest to policymakers. Researchers may be willing to make additional, minimal modeling assumptions in order to preserve the ability to estimate population average causal effects. We seek to make two contributions on this topic. First, we propose systematic definitions of propensity score overlap and non-overlap regions. Second, we develop a novel Bayesian framework to estimate population average causal effects with nominal model dependence and appropriately large uncertainties in the presence of non-overlap and causal effect heterogeneity. In this approach, the tasks of estimating causal effects in the overlap and non-overlap regions are delegated to two distinct models. Tree ensembles are selected to non-parametrically estimate individual causal effects in the overlap region, where the data can speak for themselves. In the non-overlap region, where insufficient data support means reliance on model specification is necessary, individual causal effects are estimated by extrapolating trends from the overlap region via a spline model. The promising performance of our method is demonstrated in simulations. Finally, we utilize our method to perform a novel investigation of the effect of natural gas compressor station exposure on cancer outcomes.
READ FULL TEXT