Practical procedures to deal with common support problems in matching estimation
By M. Lechner, Anthony Strittmatter. Social Science Research Network, 2017
88 citations recorded by the source corpus.
ABSTRACT This paper assesses the performance of common estimators adjusting for differences in covariates, such as matching and regression, when faced with the so-called common support problems. It also shows how different procedures suggested in the literature affect the properties of such estimators. Based on an empirical Monte Carlo simulation design, a lack of common support is found to increase the root-mean-squared error of all investigated parametric and semiparametric estimators. Dropping observations that are off support usually improves their performance, although the magnitude of the improvement depends on the particular method used.
Subfields: Statistics and Probability
View Paper: https://www.semanticscholar.org/paper/ea8805e1a4658e2d0028f59ddda9b331dbca6567
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
- The Finite Sample Performance of Inference Methods for Propensity Score Matching and Weighting Estimators (2018, unknown): “…is thin or lacking common support (or overlap) in the propensity score across treatment states, which may compromise estimation due to a non-comparability of treated and non-treated observations, see the discussion in Imbens (2004), Imbens and Wooldridge (2009), and Lechner and Strittmatter (2017).”
- Entropy Balancing for Continuous Treatments (2020, methodology): “If this is the case, the sample needs to be trimmed and the DRF is estimated on the subset of observations in order to avoid extrapolation (Crump et al. 2009; Lechner and Strittmatter 2019).”