Rubin-Style Methods
Propensity Score Methods
Matching or weighting can make treated and untreated groups comparable on measured pre-treatment characteristics.
Page 1 of 7 · Big Picture
The big picture: Propensity Score Methods
Can observed covariates make treatment groups comparable?
Why a policy analyst should care
Balancing observed treatment predictors can improve comparability, but it cannot recover overlap that is absent or remove bias from unmeasured confounders.
Follow the idea from the opening question to a practical decision. These are the conceptual moves this module will develop:
1 Question Can observed covariates make treatment groups comparable?
2 Explore Overlap and balance matter more than prediction alone
3 Formalize Weight or match on the propensity score
4 Transfer Audit a propensity analysis
Use the left and right arrow keys to move between pages.