Thinking Clearly About Correlations and Causation: Graphical Causal Models for Observational Data
Julia M. Rohrer · 2017
Correlation does not imply causation; but often, observational data are the only option, even though the research question at hand involves causality. This article introduces readers to causal inference based on observational data with the help of graphical causal models, a powerful tool to think more clearly about the interrelations between variables. It expounds on the rationale behind the statistical control of third variables, common procedures for statistical control, and what can go wrong during their implementation. Certain types of third variables—colliders and mediators—should not be controlled for, because in these cases, statistical control can actually move the estimated association farther away from the underlying causal effect. More subtle variations of such “harmful control” include the use of unrepresentative samples that can undermine the validity of causal conclusions, and conceptual problems associated with mediation analysis. Drawing valid causal inferences on the basis of observational data is not a mechanistic procedure but rather always depends on assumptions that require domain knowledge and that can be more or less plausible. However, this caveat holds not only for research based on observational data, but for all empirical research endeavors.