Efficient Estimation of Average Treatment Effects Using the Estimated Propensity Score

By Guido W. Imbens. 2000

117 citations recorded by the source corpus.

Subfields: Economics and Econometrics, Statistics and Probability

Citations in the corpus

• Estimation and Inference of Heterogeneous Treatment Effects using Random Forests (2015, neutral): “Thus, if we knew e ( x ), we would have access to a simple unbiased estimator for τ ( x ); this observation lies at the heart of methods based on propensity weighting [e.g., Hirano et al., 2003].”
• Semiparametric Difference-in-Differences Estimators (2005, unknown): “Hirano, Imbens, and Ridder (2003) consider the situation in which the average treatment effect is estimated for a given distribution of the covariates.”
• Multivariate Matching Methods That Are Monotonic Imbalance Bounding (2011, unknown): “…of interest is a function of in-sample, not expected, balance, and so this can be important (and it explains otherwise counter-intuitive results about EPBR methods, such as that matching on the estimated propensity score is more efficient than the true score, see Hirano, Imbens and Ridder 2003).”
• On the Predictive Distributions of Outcome Gains in the Presence of an Unidentified Parameter (2003, unknown): “…and Poirier 1997; Abadie, Angrist, and Imbens 1998; Heckman and Smith 1998; Hahn 1998; Dehejia and Wahba 1999; Heckman and Vytlacil 1999, 2000a, 2000b; Chib and Hamilton 2000; Heckman, Tobias and Vytlacil 2000; Hirano, Imbens, and Ridder 2000; Hirano, Imbens, Rubin, and Zhou 2000; Vytlacil 2002).”
• Sequential Matching Estimation of Dynamic Causal Models (2004, unknown): “The design 19 See for example Hirano, Imbens, and Ridder (2003) and Rosenbaum (1987).”
• A New Instrumental Method for Dealing with Endogenous Selection (2010, unknown): “22 22Indeed, Hirano et al. (2003) show that an inverse probability-weighted estimator of average treatment effects based on an estimated propensity score is asymptotically efficient, whereas the estimator based on the true propensity score may not.”
• Breaking the Curse of Horizon: Infinite-Horizon Off-Policy Estimation (2018, unknown): “This problem is of great practical importance in many application domains where deploying a new policy can be costly or risky, such as medical treatments [26], econometrics [13], recommender systems [19], education [23], Web search [18], advertising and marketing [4, 5, 38, 40].”
• Causal Effects of Monetary Shocks: Semiparametric Conditional Independence Tests with a Multinomial Propensity Score (2011, unknown): “First, as in the cross-sectional and differences-in-differences settings discussed by Hahn (1998), Heckman et al. (1998), Hirano, Imbens, and Ridder (2003), Abadie (2005), and Abadie and Imbens (2009), inference should allow for the fact that the propensity score is unknown and must be estimated.”