What is propensity score matching, and what can it not do?
PICTURE THIS: DOM IS A TREE
Simple meaning
Propensity scores estimate the probability of treatment given observed covariates
WHY — Correlation vs Causation instead of guessing?
Why interviewers care about Correlation vs Causation:
separate people who only read docs from people who shipped.
and tied to Data Science work.
Name the idea, why it exists, then one short example.
End with when you use it and one common pitfall.
STEPS — What happens step by step?
Before you speak the answer, walk the interviewer through these steps:
- 1Propensity scores estimate the
probability of treatment given observed covariates
- 2matching or weighting on
them aims to balance those covariates.
- 3It does not balance
unobserved confounders, so it is not a substitute for randomization.
- 4Overlap, specification of the
propensity model, and post-matching diagnostics determine whether the estimate is even internally plausible.
- 5Common mistake
What juniors usually get wrong.
- 6Close
When you pick this over the alternative.
EXAMPLE — See it in action
Here's a short line you can speak, broken into clear beats:
Note: Adapt this scaffold to your own project — keep it under 60–90 seconds.
Key takeaway
Propensity scores estimate the probability of treatment given observed covariates matching or weighting on them aims to balance those covariates.