In an interesting exchange between Jacob Felson and Andrew Gelman, Gelman recommends resisting the urge to "adjudicate" competing interpretations of results (or, more specifically, "picking" one significant variable as a "cause" and another significant variable as a "moderator"). Gelman writes: "Rather than trying to isolate a single causal path, consider different cases of forward casual inference. My guess is that the different stories regarding moderators etc. could motivate different thought experiments (and, ultimately, different observational studies) regarding different potential interventions."
Comments