A Matching Estimator Based on a Bilevel Optimization Problem

Díaz, Juan; Rau, Tomás; Rivera, Jorge

doi:10.1162/rest_a_00504

Cited by 11 publications

(23 citation statements)

References 23 publications

(28 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We highlight that, to impute the missing potential outcome of any unit, the blopmatching approach does not exclude a priori any unit with opposite treatment. We also highlight that the blopmatching approach does not need to fix an exogenous number of neighbors, a crucial tuning parameter in most nonparametric approaches (see Imbens and Wooldridge [2009]).…”

Section: General Frameworkmentioning

confidence: 99%

Implementing blopmatching in Stata

2021

Self Cite

View full text Add to dashboard Cite

The blopmatching estimator for average treatment effects in observational studies is a nonparametric matching estimator proposed by Díaz, Rau, and Rivera (2015, Review of Economics and Statistics 97: 803–812). This approach uses the solutions of linear programming problems to build the weighting schemes that are used to impute the missing potential outcomes. In this article, we describe blopmatch, a new command that implements these estimators.

show abstract

Section: General Frameworkmentioning

confidence: 99%

Implementing blopmatching in Stata

2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…A related approach is proposed by Schuler et al (2017). 4 A similar approach is also used by Abadie and Imbens (2011), Lee (2013), and Díaz et al (2015).…”

Section: Introductionmentioning

confidence: 99%

Mostly harmless simulations? Using Monte Carlo studies for estimator selection

Advani

Kitagawa

Słoczyński

2019

J of Applied Econometrics

View full text Add to dashboard Cite

Summary We consider two recent suggestions for how to perform an empirically motivated Monte Carlo study to help select a treatment effect estimator under unconfoundedness. We show theoretically that neither is likely to be informative except under restrictive conditions that are unlikely to be satisfied in many contexts. To test empirical relevance, we also apply the approaches to a real‐world setting where estimator performance is known. Both approaches are worse than random at selecting estimators that minimize absolute bias. They are better when selecting estimators that minimize mean squared error. However, using a simple bootstrap is at least as good and often better. For now, researchers would be best advised to use a range of estimators and compare estimates for robustness.

show abstract

“…As is well known, exact matching is not feasible when there are multiple continuous covariates and some coarsening of the covariate space is therefore needed for implementation. Among the aforementioned papers, Díaz et al (2015) is perhaps the closest to ours in spirit, since their matching estimator is also explicitly constructed to maximize covariate balancing in a data-driven manner. We view Díaz et al (2015)'s proposal as a complement to ours, though it is not yet clear how one can formally justify inference procedures for quantile and/or distributional treatment effect estimators based on matching.…”

Section: Introductionmentioning

confidence: 99%

“…Among the aforementioned papers, Díaz et al (2015) is perhaps the closest to ours in spirit, since their matching estimator is also explicitly constructed to maximize covariate balancing in a data-driven manner. We view Díaz et al (2015)'s proposal as a complement to ours, though it is not yet clear how one can formally justify inference procedures for quantile and/or distributional treatment effect estimators based on matching. Finally, although we focus on treatment effect estimators based on IPW in this paper, we note that one can alternatively use our IPS to construct PS matching estimators for the average treatment effect, see e.g.…”

Section: Introductionmentioning

confidence: 99%

Covariate Distribution Balance via Propensity Scores

Sant’Anna

Song

2018

SSRN Journal

View full text Add to dashboard Cite

The propensity score plays an important role in causal inference with observational data. However, it is well documented that under slight model misspecifications, propensity score estimates based on maximum likelihood can lead to unreliable treatment effect estimators. To address this practical limitation, this article proposes a new framework for estimating propensity scores that mimics randomize control trials (RCT) in settings where only observational data is available. More specifically, given that in RCTs the joint distritbution of covariates are balanced between treated and not-treated groups, we propose to estimate the propensity score by maxizing the covariate distribution balance. The proposed propensity score estimators, which we call the integrated propensity score (IPS), are data-driven, do not rely on tuning parameters such as bandwidths, admit an asymptotic linear representation, and can be used to estimate many different treatment effect measures in a unified manner. We derive the asymptotic properties of inverse probability weighted estimators for the average, distributional and quantile treatment effects based on the IPS and illustrate their relative performance via Monte Carlo simulations and three empirical applications. An implementation of the proposed methods is provided in the new package IPS for R.

show abstract

A Matching Estimator Based on a Bilevel Optimization Problem

Cited by 11 publications

References 23 publications

Implementing blopmatching in Stata

Implementing blopmatching in Stata

Mostly harmless simulations? Using Monte Carlo studies for estimator selection

Covariate Distribution Balance via Propensity Scores

Contact Info

Product

Resources

About