How one causes another.

Correlation does not necessarily imply causation. Lack of correlation also does not necessarily imply the lack of causation. A good example can be: “inside temperature not associated with oil burned in the furnace.” or “the sailboat “

Causal relationships are often expressed as a DAG (Directed Acyclic Graph). See also Blom2021conditional for extending it “beyond DAGs”.

Probably one of the most important questions in Causal inference is this: how can we establish causal relationships with observations and experiments? can we perform Causal inference with observational data?