The performance of estimators based on the propensity score

By Martin Huber, M. Lechner, Conny Wunsch. 2013

330 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/20d661684da15d46e12a3246689ed52d651d6678

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

Citations in the corpus

New Evidence on the Finite Sample Properties of Propensity Score Reweighting and Matching Estimators (2014, background): “1 More recently, Huber, Lechner, and Wunsch (2010, 2013) have investigated these issues as well.”
Unobservable, but unimportant? The relevance of usually unobserved variables for the evaluation of labor market policies☆ (2017, result): “However, in the long-run we find no positive effect on employment probabilities (e.g. Wolff and Jozwiak, 2007) nor a reduction of the unemployment duration (e.g. Hujer et al., 2006) as found by prior studies, for different time periods and target groups, in this literature.”
Practical procedures to deal with common support problems in matching estimation (2017, methodology): “Similar to Huber, Lechner, and Wunsch (2013), we do this 2 in the context of a large-scale active labour market policy evaluation and use Empirical Monte Carlo methods.”
How Learning a Musical Instrument Affects the Development of Skills (2013, unknown): “First, it allows us to use a large number of control variables even with a limited sample size, given that these control variables are summarized in the propensity score (Huber et al., 2013).”
Nonparametric estimation of causal heterogeneity under high-dimensional confounding (2019, methodology): “Recently, Wager and Athey (2018) follow the same ideas as in Hahn (1998) but use Causal Forests instead of standard nonparametric regression. Athey, Tibshirani, and Wager (2019) and Lechner (2018) modify the Random Forest algorithm to better adjust for confounding and improve precision.”
Income and employment effects of shale gas extraction windfalls: Evidence from the Marcellus region (2014, background): “5 A deeper discussion about bootstrapping techniques can be found in Huber et al. (2013). 6 See Shah et al. (2005) for more details on the different types of matching methods.”
The Slx Model (2015, methodology): “To examine this, we performed an empirical Monte Carlo experiment, which is termed empirical since it is design dependent (Huber et al., 2013).”
Entropy Balancing for Continuous Treatments (2020, methodology): “as shown by Huber et al. (2020) for their kernel-averaging estimator.”
Direct and indirect treatment effects–causal chains and mediation analysis with instrumental variables (2014, unknown): “Similarly to Huber et al. (2013) and Frölich and Huber (2014b), the trimmed versions discard observations that would obtain a relative weight that is larger than 5% in the estimation of some mean potential outcome.”
Radius matching on the propensity score with bias adjustment: tuning parameters and finite sample behaviour (2014, methodology): “Huber et al. (2013), henceforth referred to as HLW13, assess the finite sample properties of a broad range of different (classes of) estimators of the average treatment effect on the treated (ATET) by constructing a—what they call—Empirical Monte Carlo Study (EMCS) which is based on empirical…”
The Finite Sample Performance of Inference Methods for Propensity Score Matching and Weighting Estimators (2018, methodology): “Huber, Lechner, and Wunsch (2013) suggested using a trimming procedure first discussed in Imbens (2004), which is asymptotically unbiased if common support holds asymptotically.”
Testing the Unconfoundedness Assumption via Inverse Probability Weighted Estimators of (L)ATT (2014, background): “The basic idea, as described by Huber et al. (2013), is to build a data-generating process in which the number of variables, their distributions, and the relationships between them are based on empirical quantities from a relevant dataset (the AAI version of the JTPA data in our case).”