New Evidence on the Finite Sample Properties of Propensity Score Reweighting and Matching Estimators

By Matias Busso, John E. Dinardo, J. McCrary. Review of Economics and Statistics, 2014

405 citations recorded by the source corpus.

Subfields: Economics and Econometrics, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/c328484f5bb0694f71066fe038ceb50fca96eeb3

How researchers see this paper

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

In Economics and Econometrics

In Statistics and Probability

Citations in the corpus

Bootstrap Inference of Matching Estimators for Average Treatment Effects (2017, positive): “Based on Frölich (2004) and Busso, DiNardo, and McCrary (2014), we consider the following data-generating process for {Yi,Di,Xi}Ni=1, Yi(1) = τ + m(‖Xi‖) + i, Yi(0) = m(‖Xi‖) + i, Di = I{P(Xi) ≥ νi}, νi ∼ U [0, 1], P(Xi) = γ1 + γ2 ‖Xi‖ , Xi = (X1i, . . . ,Xki)′, Xji = ξi|ζ ji|/ ‖ζi‖ for j = 1, . .…”
Practical procedures to deal with common support problems in matching estimation (2017, background): “For example, Abadie and Imbens (2011) and Busso, DiNardo, and McCrary (2014b) propose to apply more structural empirical simulation designs.”
Difference-in-Differences with multiple time periods (2018, background): “In practice, this modification usually translates to estimators with improved finite sample properties, see e.g. Busso et al. (2014).”
Housing and Employment Insecurity among the Working Poor (2016, methodology): “If treatment selection depends on the covariates used to estimate the propensity score, then samples balanced on propensity scores allow unbiased estimates of the average treatment effect for the treated (ATT) in expectation (Rosenbaum and Rubin 1983).”
Econometric Methods for Program Evaluation (2018, background): “This estimator can be modified so that the weights in each treatment arm sum to one, which produces improvements in finite sample performance (see, e.g., Busso et al., 2014).”
Balancing Covariates via Propensity Score Weighting (2014, background): “Fourth, with ATE and ATT extreme probabilities (close to 0 or 1) introduce extreme IPWs, with adverse finite-sample consequences such as poor balance and large variance (Busso et al., 2014).”
The Finite Sample Performance of Inference Methods for Propensity Score Matching and Weighting Estimators (2018, neutral): “We refer to Busso, DiNardo, and McCrary (2014) for more details on the simulation design.”
Shock-Based Causal Inference in Corporate Finance and Accounting Research (2015, background): “For trimming to common support, see Crump et al. (2009); for matching, see Rosenbaum (2010); for inverse propensity weighting, see Busso et al. (2014).”
Acquisitions, markups, efficiency, and product quality: Evidence from India (2018, background): “While recent research argues that propensity score reweighting is more efficient compared to nearest neighbour matching (Busso et al., 2014), nearest neighbour matching has been more popular in the analysis of foreign acquisitions.”
Cross-Border M&As and Innovative Activity of Acquiring and Target Firms (2016, methodology): “…fixed effects as a control for unobserved heterogeneity, a fixed-effects Poisson model, and a linear fixed-effects model using the patent stock rather 37 See e.g. Caliendo and Kopeinig (2008) for an overview of these methods and Busso et al. (2014) for an analysis of their finite-sample properties.”