LATE
The Local Average Treatment Effect: the average treatment effect for compliers — the subpopulation whose treatment status is moved by the instrument (Imbens & Angrist 1994). Under instrument independence, the Exclusion-Restriction, Monotonicity, and a first stage, IV identifies the LATE, not the overall ATE (Causal-Estimand). Its value is interpretive: it names for whom an IV estimate is valid, which is why it anchors the credibility of instrumental-variables work.
Relied on by
Instrumental variables (IV) and fuzzy designs (including fuzzy RD).
Referenced by
- Angrist2022-EmpiricalStrategiesIlluminatingPath
- AngristKrueger1999-EmpiricalStrategiesLaborEconomics
- DeChaisemartinDHaultfoeuille2018-FuzzyDiD
- Method-buildout pass (2026-06-17): Imbens2014-IVEconometriciansPerspective, AngristKrueger2001-SearchForIdentification, Murray2006-WeakAndInvalidInstruments (implicit), fuzzy RD in LeeLemieux2010-RDDInEconomics and ImbensLemieux2008-RDDGuideToPractice, noncompliance in AtheyImbens2017-EconometricsOfRandomizedExperiments, external- validity discussion in LudwigEtAl2011-MechanismExperiments and ImbensWooldridge2009-ProgramEvaluation.