Why can't causation be inferred from correlational studies?

Causation cannot be inferred from correlational studies because they do not control or manipulate variables. When conducting a correlational study, the researchers investigate the potential relationship between two or more pre-existing variables.

Without manipulating and controlling variables, it is impossible for the researchers to rule out other explanations for any observed relationships. It is possible that a third unmeasured variable could be responsible for the relationship. For example, some correlational studies have indicated a relationship between coffee consumption and lung cancer. However it is entirely possible that people who drink more coffee might also smoke more.

In short, correlational studies investigate relationships between variables, but because they lack the rigorous manipulation and control found in true experiments, cause-and-effect relationships cannot be established.