Causal reasoning · Claim boundaries
Association vs Causation
What must be true before an observed difference can be interpreted as an effect?
Page 1 of 7 · Big Picture
The big picture: Association vs Causation
What claim does the study design support?
Why a policy analyst should care
Observed groups can differ for reasons other than the exposure, so the study design—not the strength of a regression coefficient—sets the boundary of a causal claim.
Follow the idea from the opening question to a practical decision. These are the conceptual moves this module will develop:
1 Question What claim does the design support?
2 Explore Build the claim from the evidence
3 Formalize Observed and counterfactual questions
4 Transfer Audit an insurance claim
Use the left and right arrow keys to move between pages.