Mixing treated and control samples to shrink propensity scores yields a weighting estimator that reduces finite-sample variance for ATT estimation without changing the estimand, at the cost of a tuning parameter delta.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ME 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Mixing Samples to Address Weak Overlap in Causal Inference
Mixing treated and control samples to shrink propensity scores yields a weighting estimator that reduces finite-sample variance for ATT estimation without changing the estimand, at the cost of a tuning parameter delta.