Double machine learning-based programme evaluation under unconfoundedness

Econometric methods for program evaluation

Michael Knaus

The Econometrics Journal, 2022, vol. 25, issue 3, 602-627

Abstract: SummaryThis paper reviews, applies, and extends recently proposed methods based on double machine learning (DML) with a focus on programme evaluation under unconfoundedness. DML-based methods leverage flexible prediction models to adjust for confounding variables in the estimation of (a) standard average effects, (b) different forms of heterogeneous effects, and (c) optimal treatment assignment rules. An evaluation of multiple programmes of the Swiss Active Labour Market Policy illustrates how DML-based methods enable a comprehensive programme evaluation. Motivated by extreme individualised treatment effect estimates of the DR-learner, we propose the normalised DR-learner (NDR-learner) to address this issue. The NDR-learner acknowledges that individualised effect estimates can be stabilised by an individualised normalisation of inverse probability weights.

Keywords: Causal machine learning; conditional average treatment effects; DR-learner; individualised treatment rules; multiple treatments; policy learning (search for similar items in EconPapers)
Date: 2022
References: Add references at CitEc
Citations: View citations in EconPapers (27)

Downloads: (external link)
http://hdl.handle.net/10.1093/ectj/utac015 (application/pdf)
Access to full text is restricted to subscribers.

Related works:
Working Paper: Double Machine Learning based Program Evaluation under Unconfoundedness (2022)
Working Paper: Double Machine Learning Based Program Evaluation under Unconfoundedness (2020)
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:oup:emjrnl:v:25:y:2022:i:3:p:602-627.

Access Statistics for this article

The Econometrics Journal is currently edited by Jaap Abbring

More articles in The Econometrics Journal from Royal Economic Society Contact information at EDIRC.
Bibliographic data for series maintained by Oxford University Press ().