Premium
Sharp Bounds on Causal Effects under Sample Selection
Author(s) -
Huber Martin,
Mellace Giovanni
Publication year - 2015
Publication title -
oxford bulletin of economics and statistics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.131
H-Index - 73
eISSN - 1468-0084
pISSN - 0305-9049
DOI - 10.1111/obes.12056
Subject(s) - selection (genetic algorithm) , parametric statistics , econometrics , bounded function , outcome (game theory) , identification (biology) , average treatment effect , selection bias , sample (material) , mathematics , population , treatment effect , voucher , statistics , economics , computer science , mathematical economics , propensity score matching , medicine , physics , artificial intelligence , traditional medicine , botany , accounting , mathematical analysis , biology , thermodynamics , environmental health
Abstract In many empirical problems, the evaluation of treatment effects is complicated by sample selection so that the outcome is only observed for a non‐random subpopulation. In the absence of instruments and/or tight parametric assumptions, treatment effects are not point identified, but can be bounded under mild restrictions. Previous work on partial identification has primarily focused on the ‘always observed’ (irrespective of the treatment). This article complements those studies by considering further populations, namely the ‘compliers’ (observed only if treated) and the observed population. We derive sharp bounds under various assumptions and provide an empirical application to a school voucher experiment.