What question did this study set out to answer?

Determine how to achieve semiparametrically efficient estimation of average treatment effects for binary treatments under unconfounded assignment.

July 1, 2003Econometrica

Efficient Estimation of Average Treatment Effects Using the Estimated Propensity Score

View Full Paper

Ask AI

Bookmark

Authors

KHKeisuke HiranoToyohashi Heart Center GIGuido W. ImbensNorthwestern University GRGeert RidderUniversity of Southern California

Discussion

Member takes

Implication

Theoretical analysis demonstrates efficient average treatment effect estimation under unconfoundedness via inverse weighting by estimated propensity scores, indicating optimal precision over true...

Key Points

Determine how to achieve semiparametrically efficient estimation of average treatment effects for binary treatments under unconfounded assignment.
Analyzed inverse probability weighting estimators using nonparametrically estimated propensity scores rather than true assignment probabilities.
Assumed exogenous treatment assignment (unconfoundedness conditional on observed covariates) for scalar outcomes.
Formulated the estimator within an empirical likelihood framework to characterize how auxiliary propensity information is incorporated.
Weighting by the inverse of a nonparametric estimate of the propensity score achieves the semiparametric efficiency bound for the average treatment effect.
Using estimated propensity scores yields strictly greater asymptotic precision than conditioning on or weighting by known, true propensity scores.
The proposed weighting method is mathematically equivalent to an empirical likelihood estimator that efficiently integrates propensity score constraints.

Cite This Study

Hirano et al. (2003) studied this question.

synapsesocial.com/papers/69d76e66086f9d6299f30f65 https://doi.org/10.1111/1468-0262.00442

View Full Paper

Ask AI

Bookmark

July 1, 2003Econometrica

Efficient Estimation of Average Treatment Effects Using the Estimated Propensity Score

View Full Paper

Ask AI

Bookmark

Authors

KHKeisuke HiranoToyohashi Heart Center GIGuido W. ImbensNorthwestern University GRGeert RidderUniversity of Southern California

Discussion

Member takes

Implication

Theoretical analysis demonstrates efficient average treatment effect estimation under unconfoundedness via inverse weighting by estimated propensity scores, indicating optimal precision over true...

Key Points

Determine how to achieve semiparametrically efficient estimation of average treatment effects for binary treatments under unconfounded assignment.
Analyzed inverse probability weighting estimators using nonparametrically estimated propensity scores rather than true assignment probabilities.
Assumed exogenous treatment assignment (unconfoundedness conditional on observed covariates) for scalar outcomes.
Formulated the estimator within an empirical likelihood framework to characterize how auxiliary propensity information is incorporated.
Weighting by the inverse of a nonparametric estimate of the propensity score achieves the semiparametric efficiency bound for the average treatment effect.
Using estimated propensity scores yields strictly greater asymptotic precision than conditioning on or weighting by known, true propensity scores.
The proposed weighting method is mathematically equivalent to an empirical likelihood estimator that efficiently integrates propensity score constraints.

Cite This Study

Hirano et al. (2003) studied this question.

synapsesocial.com/papers/69d76e66086f9d6299f30f65 https://doi.org/10.1111/1468-0262.00442

Also Consider

Synapse has enriched 3 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark