Causal structure discovery algorithms
Informally, causation is defined as a relationship between two variables X and Y such that changes in X lead to changes in Y8. The key difference between association and causation lies in the potential of confounding. Suppose that no direct causal relationship exists between X and Y but rather a third variable Z causes both X and Y. In this case, even though X and Y are strongly associated, altering X will not lead to changes in Y. Z is called a confounder. More formally, causation is a direct effect between A and B that remains after adjusting for confounding. Confounding can be observed or unobserved (latent).
Causal structure is the set of causal relationships among a set of variables, and causal structure discovery is the problem of learning the causal structure from observational data. Dedicated causal structure discovery algorithms exist and…
