Relaxing conditions for local average treatment effect in fuzzy regression discontinuity

Choi, Jin-young; Lee, Myoung-Jae

doi:10.1016/j.econlet.2018.09.010

Cited by 9 publications

(5 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Here we provide the details on the indirect approach for FRD similar to (2), drawing partly on Choi and Lee (2018b). The discussion here reveals what kind of conditions are needed for the indirect approach, and why it fails in binary treatment extrapolation for binary outcome.…”

Section: Appendix B: Indirect Ratio-based Approach For Frd Extrapolationmentioning

confidence: 99%

Regression Discontinuity for Binary Response and Local Maximum Likelihood Estimator to Extrapolate Treatment

Lee

2022

Eval Rev

Self Cite

View full text Add to dashboard Cite

Regression discontinuity is popular in finding treatment/policy effects when the treatment is determined by a continuous variable crossing a cutoff. Typically, a local linear regression (LLR) estimator is used to find the effects. For binary response, however, LLR is not suitable in extrapolating the treatment, as in doubling/tripling the treatment dose/intensity. The reason is that doubling/tripling the LLR estimate can give a number out of the bound [Formula: see text], despite that the effect should be a change in probability. We propose local maximum likelihood estimators which overcome these shortcomings, while giving almost the same estimates as the LLR estimator does for the original treatment. A simulation study and an empirical analysis for effects of an income subsidy program on religion demonstrate these points.

show abstract

Section: Appendix B: Indirect Ratio-based Approach For Frd Extrapolationmentioning

confidence: 99%

Regression Discontinuity for Binary Response and Local Maximum Likelihood Estimator to Extrapolate Treatment

Lee

2022

Eval Rev

Self Cite

View full text Add to dashboard Cite

show abstract

“…A somewhat more restrictive definition of types of units is used by Bertanha and Imbens (2020), who assume that, given the value of the cutoff c, the decision to take the treatment is only a function of the score via the indicator 1(X i ≥ c), implying that a unit's compliance type is constant for all values of the score with equal treatment assignment. Other related approaches are discussed in Imbens and Lemieux (2008), Frandsen, Frolich, and Melly (2012), Cattaneo, Keele, Titiunik, and Vazquez-Bare (2016), and Choi and Lee (2018).…”

Section: Fuzzy Designsmentioning

confidence: 99%

Regression Discontinuity Designs

Cattaneo¹,

Titiunik²

2021

Preprint

View full text Add to dashboard Cite

The Regression Discontinuity (RD) design is one of the most widely used non-experimental methods for causal inference and program evaluation. Over the last two decades, statistical and econometric methods for RD analysis have expanded and matured, and there is now a large number of methodological results for RD identification, estimation, inference, and validation. We offer a curated review of this methodological literature organized around the two most popular frameworks for the analysis and interpretation of RD designs: the continuity framework and the local randomization framework. For each framework, we discuss three main areas: (i) designs and parameters, which focuses on different types of RD settings and treatment effects of interest; (ii) estimation and inference, which presents the most popular methods based on local polynomial regression and analysis of experiments, as well as refinements, extensions and other methods; and (iii) validation and falsification, which summarizes an array of mostly empirical approaches to support the validity of RD designs in practice.

show abstract

“…as well as E Y 0 jS ð Þ, where (D 1 , D 0 ) are the 'potential treatments' corresponding to 1 0 ≤ S ½ ¼0, 1; see Choi and Lee (2018) and references therein. In this paper, we eschew addressing fuzzy RD except for one occasion, as it is far more involved than sharp RD.…”

Section: Mean Untreated Response Continuity For Identificationmentioning

confidence: 99%

“…The above ID finding is for ‘sharp RD’. For ‘fuzzy RD’ with D determined by S and some other random variables so that

D \neq 1 ([], 0 \leq S)

, the requisite ID conditions are more involved, requiring the continuity of

E ({}|, ((), Y^{1} - Y^{0}) D^{0}, S)

as well as

E (()|, Y^{0}, S)

, where (

D^{1}

D^{0}

) are the ‘potential treatments’ corresponding to

1 ([], 0 \leq S) = 0, 1

; see Choi and Lee (2018) and references therein. In this paper, we eschew addressing fuzzy RD except for one occasion, as it is far more involved than sharp RD.…”

Section: Rd Identification and Intent To Treatmentioning

confidence: 99%

Score manipulation, density continuity and intent‐to‐treat effect for regression discontinuity

Choi

Lee

2021

Pacific Economic Review

View full text Add to dashboard Cite

Regression discontinuity (RD) is widely used in many disciplines of science to find treatment effect when the treatment is determined by an underlying running variable (‘score') crossing a cutoff or not. The main attraction of RD is local randomization around , which is, however, often ruined by manipulation on . To detect manipulation, the continuity of score density function at is routinely tested in practice. In this paper, we examine how informative is for RD, and show the following. First, for incumbency effect in election to which RD has been heavily applied, may have no information content. Second, for RD in general, the continuity is neither necessary nor sufficient for RD validity. Third, if the treatment cannot be implemented without manipulation of , then the manipulation had better be considered as part of the treatment effect, much as in ‘intent‐to‐treat effect’ for clinical trials. These findings call for relying less on continuity tests and, instead, thinking more about how subjects react to the treatment to modify their , how to design the treatment to lessen manipulation, and what to take as the desired treatment effect.

show abstract

Relaxing conditions for local average treatment effect in fuzzy regression discontinuity

Cited by 9 publications

References 9 publications

Regression Discontinuity for Binary Response and Local Maximum Likelihood Estimator to Extrapolate Treatment

Regression Discontinuity for Binary Response and Local Maximum Likelihood Estimator to Extrapolate Treatment

Regression Discontinuity Designs

Score manipulation, density continuity and intent‐to‐treat effect for regression discontinuity

Contact Info

Product

Resources

About