Wanna Get Away? Regression Discontinuity Estimation of Exam School Effects Away From the Cutoff

By Joshua D. Angrist, Miikka Rokkanen. 2015

220 citations recorded by the source corpus.

In regression discontinuity (RD) studies exploiting an award or admissions cutoff, causal effects are nonparametrically identified for those near the cutoff. The effect of treatment on inframarginal applicants is also of interest, but identification of such effects requires stronger assumptions than those required for identification at the cutoff. This article discusses RD identification and estimation away from the cutoff. Our identification strategy exploits the availability of dependent variable predictors other than the running variable. Conditional on these predictors, the running variable is assumed to be ignorable. This identification strategy is used to study effects of Boston exam schools for inframarginal applicants. Identification based on the conditional independence assumptions imposed in our framework yields reasonably precise and surprisingly robust estimates of the effects of exam school attendance on inframarginal applicants. These estimates suggest that the causal effects of exam school attendance for 9th grade applicants with running variable values well away from admissions cutoffs differ little from those for applicants with values that put them on the margin of acceptance. An extension to fuzzy designs is shown to identify causal effects for compliers away from the cutoff. Supplementary materials for this article are available online.

Subfields: Economics and Econometrics, Education, Statistics and Probability

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 Education

In Statistics and Probability

Citations in the corpus

Regression Discontinuity Designs Using Covariates (2018, background): “, Angrist and Rokkanen, 2015; Keele, Titiunik, and Zubizarreta, 2015). However, local randomization is a stronger identification assumption than continuity of conditional expectations—Sekhon and Titiunik (2016) give a detailed discussion on this point, including examples and counterexamples.”
A Practical Introduction to Regression Discontinuity Designs (2019, background): “…assumptions about 18 (i) the regression functions near the cutoff (Dong and Lewbel, 2015; Wing and Cook, 2013), (ii) local independence assumptions (Angrist and Rokkanen, 2015) (iii) exploiting specific features of the design such as imperfect compliance (Bertanha and Imbens, 2019), or (iv) the…”
Elite Colleges and Upward Mobility to Top Jobs and Top Incomes (2019, unknown): “These results are consistent with a broader literature arguing that elite education at the high school level (Dobbie and Fryer 2014; Abdulkadiroğlu, Angrist, and Pathak 2014; Angrist and Rokkanen 2015) has little effect on learning outcomes.”
Econometric Methods for Program Evaluation (2018, background): “While there is some very recent work that addresses the issue of extrapolation of RD treatment effects (e.g., Angrist and Rokkanen, 2015; Dong and Lewbel, 2015; Bertanha and Imbens, 2017; Cattaneo et al., 2017f), more work is certainly needed, covering both methodological and empirical issues.”
A regression discontinuity design for ordinal running variables: Evaluating central bank purchases of corporate bonds (2019, background): “An influential alternative approach is due to Angrist and Rokkanen (2015) (AR hereafter), who propose to identify causal effects away from the threshold by relying on a conditional independence assumption (CIA).”
External Validity in Fuzzy Regression Discontinuity Designs (2019, unknown): “Angrist and Rokkanen (2015) exploited the presence of pretreatment covariates, and assess whether conditional on these covariates the dependence between the forcing variable and outcome vanishes.”
Regression Discontinuity Designs (2021, unknown): “Dong and Lewbel (2015) and Cerulli, Dong, Lewbel, and Poulsen (2017) study local extrapolation methods via derivatives of the RD average treatment effect in the continuitybased framework, while Angrist and Rokkanen (2015) employ pre-intervention covariates under a conditional ignorability condition ”