Positivity and overlap

Strengthen treatment selection, separate the propensity score distributions, and inspect what happens to weights and estimates.

What is the positivity assumption?

Positivity requires a nonzero probability of each treatment for every covariate pattern in the target population. In finite data, poor overlap is the practical warning: comparable treated and untreated people become rare.

Try it in the experiment

Start with the visual support experiment: common, rare, or impossible comparisons →

  1. Compare the groups under moderate treatment selection.
  2. Switch to strong selection.
  3. Inspect the propensity distributions, clipped probabilities, and effective sample sizes.

Extreme weights concentrate information in a few observations, while outcome models rely more heavily on extrapolation. AIPW combines the two approaches; it does not manufacture comparisons that the data do not contain.