dShrink is a model-free transfer estimator using summary statistics that is guaranteed to have lower expected quadratic error than the target-only estimator under arbitrary population heterogeneity.
L., Chang, T.-H., Nguyen, T
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
stat.ME 2verdicts
UNVERDICTED 2representative citing papers
ECO-ATE is a federated semiparametrically efficient estimator for the average treatment effect on a target population that incorporates summary statistics from source populations while allowing distributional shifts.
citing papers explorer
-
Divide-and-shrink: An efficient and heterogeneity-agnostic approach for transfer estimation using summary statistics
dShrink is a model-free transfer estimator using summary statistics that is guaranteed to have lower expected quadratic error than the target-only estimator under arbitrary population heterogeneity.
-
Efficient collaborative learning of the average treatment effect
ECO-ATE is a federated semiparametrically efficient estimator for the average treatment effect on a target population that incorporates summary statistics from source populations while allowing distributional shifts.