Cause and Effect Relationship.
Nothing beats a simple, elegant, controlled, randomized experiment if you want to make strong claims about causality.
Causal inference is a difficult and slippery topic, which cannot be answered with observational data alone without additional assumptions.
Causation comes generally from directed research. From the raw data, you got generally a correlation but not a causation. An other approach is to say that if X causes Y, then the noise affecting X will also affect Y.
Strong causal claims require:
- Random and representative samples
- No confounds (impossible)