Practically Effective Adjustment Variable Selection in Causal Inference
This work addresses a practical challenge in causal inference for researchers and practitioners dealing with real-world data limitations, though it is incremental as it builds on existing methods for variable selection.
The paper tackles the problem of selecting adjustment variables for causal effect estimation when data is limited and variable sets are not uniquely determined, proposing criteria and an algorithm that prevent accuracy degradation and demonstrating its utility on existing and artificial data.
In the estimation of causal effects, one common method for removing the influence of confounders is to adjust the variables that satisfy the back-door criterion. However, it is not always possible to uniquely determine sets of such variables. Moreover, real-world data is almost always limited, which means it may be insufficient for statistical estimation. Therefore, we propose criteria for selecting variables from a list of candidate adjustment variables along with an algorithm to prevent accuracy degradation in causal effect estimation. We initially focus on directed acyclic graphs (DAGs) and then outlines specific steps for applying this method to completed partially directed acyclic graphs (CPDAGs). We also present and prove a theorem on causal effect computation possibility in CPDAGs. Finally, we demonstrate the practical utility of our method using both existing and artificial data.