On the Role of the Propensity Score in Efficient Semiparametric Estimation of Average Treatment Effects

By Jinyong Hahn. 1998

Subfields: Statistics and Probability, Causal Inference & Discovery

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Statistics and Probability

In Causal Inference & Discovery

Citations in the corpus

Deep Neural Networks for Estimation and Inference: Application to Causal Effects and Other Semiparametric Estimands (2018, methodology): “Hahn (1998) showed that the inﬂuence function for a single average potential outcome is given by ψ t ( z ) − E [ Y(t) ] , for t ∈ { 0 !”
Double/Debiased/Neyman Machine Learning of Treatment Effects (2017, methodology): “Neyman-orthogonal scores are readily available for both the ATE and ATTE – they turn out to be the doubly robust/efficient scores of Robins and Rotnitzky (1995) and Hahn (1998). For estimating the ATE, we employ”
The State of Applied Econometrics - Causality and Policy Evaluation (2016, neutral): “In that case many estimation strategies have been developed, relying on regression Hahn [1998], matching Abadie and Imbens [2006], inverse propensity weighting Hirano et al. [2001], subclassification Rosenbaum and Rubin [1983a], as well as doubly robust methods Robins and Rotnitzky [1995], Robins et”
Approximate residual balancing: debiased inference of average treatment effects in high dimensions (2016, background): “·/ or the outcome fit β̂c is consistent, and they are asymptotically efficient in a semiparametric specification (Hahn, 1998; Hirano et al., 2003; Robins and Rotnitzky, 1995; Tsiatis, 2007).”
Double Reinforcement Learning for Efficient Off-Policy Evaluation in Markov Decision Processes (2019, methodology): “However, DM can fail to be efficient even under M1 unless q-functions are parametric (and correctly specified) or extremely smooth (as shown by Hahn, 1998 but only in the T = 0 case).”
Supplementary Appendix for"Inference on Treatment Effects After Selection Amongst High-Dimensional Controls" (2013, positive): “The efficient moment condition, derived by Hahn (1998), for parameter γ0 is as follows: E [ϕ̃(γ0, yi, di, g(0, zi), g(1, zi),m(zi), µ)] = 0,(2.23) where µ = E[m(zi)] = P(di = 1), and ϕ̃(γ, y, d, g0, g1,m, µ) = d(y − g1) µ − m(1− d)(y − g0) (1−m)µ + d(g1 − g0) µ − γ d µ .”
Nonparametric Tests for Treatment Effect Heterogeneity (2008, neutral): “Various estimators have been proposed for the average treatment eﬀect in this setting, e.g., Hahn (1998), Heckman, Ichimura and Todd (1998), Hirano, Imbens and Ridder (2003), Chen, Hong, and Tarozzi (2004), and Abadie and Imbens (2006).”
Efficient Policy Learning (2017, methodology): “…bounds available for different policy learners, and concretely establishes the relevance of the classic literature on semiparametrically efficient estimation (Bickel et al., 1998; Hahn, 1998; Hirano et al., 2003; Newey, 1994; Robins and Rotnitzky, 1995; Robins et al., 1995) to policy learning.”
Automated versus Do-It-Yourself Methods for Causal Inference: Lessons Learned from a Data Analysis Competition (2017, background): “A parallel argument, however, is that if the response surface is modeled correctly it is not necessary to preprocess the data in this way (Hahn, 1998; Hill, 2011).”
Program evaluation with high-dimensional data (2013, methodology): “In the general endogenous treatment effects setting, we build the moment conditions satisfying (1.2) from the efficient influence functions for certain reduced form parameters, building upon Hahn (1998).”
Matching and semi-parametric IV estimation, a distance-based measure of migration, and the wages of young men (2011, background): “A nonexhaustive list of recent contributions in the economics literature includes Abadie and Imbens (2002), Hahn (1998), Heckman, Ichimura and Todd (1997, 1998), Heckman, Ichimura, Smith and Todd (1998), and Hirano, Imbens and Ridder (2003).”
Estimation of Causal Effects using Propensity Score Weighting: An Application to Data on Right Heart Catheterization (2001, background): “Some rely on estimating the conditional regression function of the outcomes given covariates (e.g., Robins, Rotnitzky and Zhao, 1995; Robins and Rotnitzky, 1995; Hahn, 1998; Heckman, Ichimura and Todd, 1997, 1998).”
Minimal dispersion approximately balancing weights: asymptotic properties and practical considerations (2017, background): “The conclusion follows from Si taking the same form as the efficient score (Hahn, 1998).”
Econometric Evaluation of Social Programs, Part II: Using the Marginal Treatment Effect to Organize Alternative Econometric Estimators to Evaluate Social Programs, and to Forecast their Effects in New Environments (2007, methodology): “] Hahn, Todd and Van der Klaauw (2001) present an exposition of the regression discontinuity estimator within a LATE framework. This section exposits the regression discontinuity method within our MTE framework. Suppose assumptions (A-1)–(A-5) hold except that we relax independence assumption (A-1) ”
Non-Parametric Regression for Binary Dependent Variables (2006, background): “Examples are partial means, average treatment effects or average derivative estimators, (see e.g. Blundell and Powell 2004; Frölich 2004, 2005, 2006; Hahn 1998; Heckman et al. 1998; Hirano et al. 2003; Imbens 2004).”