Extrapolate-Ing: External Validity and Overidentification in the Late Framework

By J. Angrist, Iv'an Fern'andez-Val. 2010

172 citations recorded by the source corpus.

Subfields: Economics and Econometrics, Gender Studies, General Health Professions

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 Gender Studies

In General Health Professions

Citations in the corpus

The State of Applied Econometrics - Causality and Policy Evaluation (2016, neutral): “Angrist and Fernandez-Val [2010] consider extrapolating local average treatment effects by exploiting the presence of other exogenous covariates.”
External Validity in Fuzzy Regression Discontinuity Designs (2019, unknown): “The study has conditional external validity if, Gi ⊥ ( Yi(0), Yi(1) ) ∣∣∣ Xi, Vi (15) This is a generalized version of the “conditional effect ignorability” assumption of Angrist and Fernandez-Val (2010).”
The Demand for Effective Charter Schools (2018, unknown): “Atheoretical covariate-based approaches to extrapolation reweight experimental or quasi-experimental treatment effect estimates to match the distribution of observed characteristics in a new population (see, e.g., Hotz, Imbens, and Mortimer 2005; Angrist and Fernandez-Val 2013).”
Beyond LATE with a discrete instrument. Heterogeneity in the quantity-quality interaction of children (2012, methodology): “In contrast, the approaches to test the exernal validity of LATE proposed by Angrist and Fernandez-Val (2010), Heckman, Schmierer, and Urzua (2010), and Heckman and Schmierer (2010) require either two (or more) instruments or one instrument that takes multiple values.”
Covariate balancing propensity score (2014, background): “Another potential application is the estimation of average treatment effects from the instrumental variable estimate (Angrist and Fernandez-Val, 2010).”
Selection into Identification in Fixed Effects Models, with Application to Head Start (2019, unknown): “Analogous assumptions are made in the IV literature extrapolating from compliers to a target population (Angrist and Fernandez-Val 2013; Aronow and Carnegie 2013).”
Community Colleges and Upward Mobility (2019, background): “(31)Heckman and Urzua (2010), Hull (2018b), and Kline and Walters (2016) provide related derivations, as do Angrist and Imbens (1995) for the case of ordered multivalued treatments.”
Racial Bias in Bail Decisions ⇤ (2018, unknown): “[4] Angrist, Joshua, and Iván Fernández-Val, “ExtrapoLATE-ing: External Validity and Overidentification in the LATE Framework,” in Advances in Economics and Econometrics: Volume 3, Econometrics: Tenth World Congress, Cambridge University Press, 51 (2013), 401-434.”
A Review of Generalizability and Transportability (2021, methodology): “…can use nonparametric post-stratification (also known as direct adjustment or subclassification), as has been done in the literature with randomized data (Miettinen, 1972; Prentice et al., 2005) and with observational data in the context of instrumental variables (Angrist and Fernández-Val, 2013).”
Beyond LATE with a Discrete Instrument (2017, methodology): “…remain nearly uninformative even if we impose the IV assumptions. beyond late with a discrete instrument 987 everyone with the same observed characteristics or that treatment effects vary but individuals do not sort on the unobserved gain from treatment (see, e.g., Angrist and Fernandez-Val 2013).”
Tolerating defiance? Local average treatment effects without monotonicity (2017, methodology): “…be summarized as follows: reporting only the bounds might leave out relevant information; the LATE of compliers can give researchers an idea of the magnitude of the treatment effect; under some assumptions this LATE can be extrapolated to other populations (see Angrist and Fernandez-Val (2013)).”
Econometric Methods for Program Evaluation (2018, unknown): “For a discussion of extrapolation of LATE estimates and related problems, see Angrist and Fernandez-Val (2013).”
Causal Effects of Paternity Leave on Children and Parents (2015, unknown): “This is obtained by taking the ratio of the first stage across a particular covariate group to the overall first-stage (Angrist and Pischke (2009), Angrist and Fernandez-Val (2010)).”
From Local to Global: External Validity in a Fertility Natural Experiment (2015, unknown): “Angrist (2004), Angrist and Fernandez-Val (2010), and Aronow and Carnegie (2013) considered extrapolation from local average treatment effects identiﬁed by instrumental variables to a target population.”
Social Media, News Consumption, and Polarization: Evidence from a Field Experiment (2020, background): “The reweighted estimates measure the average treatment effect under the conditional effect ignorability assumption (Angrist and Fernandez-Val, 2013; Aronow and Carnegie, 2013).”