Obtaining Causal Information by Merging Datasets with MAXENT
This addresses a key challenge in causal inference for scientific disciplines where joint observations are limited, offering a method to extract causal knowledge from fragmented data.
The paper tackles the problem of inferring causal effects when not all treatment and target variables are observed jointly, by merging statistical information from different datasets using the maximum entropy principle, showing that edges among variables can be identified under assumptions of causal sufficiency and an extended faithfulness.
The investigation of the question "which treatment has a causal effect on a target variable?" is of particular relevance in a large number of scientific disciplines. This challenging task becomes even more difficult if not all treatment variables were or even cannot be observed jointly with the target variable. Another similarly important and challenging task is to quantify the causal influence of a treatment on a target in the presence of confounders. In this paper, we discuss how causal knowledge can be obtained without having observed all variables jointly, but by merging the statistical information from different datasets. We show how the maximum entropy principle can be used to identify edges among random variables when assuming causal sufficiency and an extended version of faithfulness, and when only subsets of the variables have been observed jointly.