Sharp IV bounds on average treatment effects on the treated and other populations under endogeneity and noncompliance

Martin Huber, Lukas Laffers, Giovanni Mellace

Research output: Contribution to journalJournal articleResearchpeer-review

66 Downloads (Pure)

Abstract

In the presence of an endogenous binary treatment and a valid binary instrument, causal effects are point identified only for the subpopulation of compliers, given that the treatment is monotone in the instrument. With the exception of the entire population, causal inference for further subpopulations has been widely ignored in econometrics. We invoke treatment monotonicity and/or dominance assumptions to derive sharp bounds on the average treatment effects on the treated, as well as on other groups. Furthermore, we use our methods to assess the educational impact of a school voucher program in Colombia and discuss testable implications of our assumptions.
Original languageEnglish
JournalJournal of Applied Econometrics
Volume32
Pages (from-to)56-79
ISSN0883-7252
DOIs
Publication statusPublished - 2017

Fingerprint

Colombia
econometrics
school
Group
Endogeneity
Average treatment effect
Noncompliance
Econometrics
Education
Monotonicity
Causal effect
Causal inference
School vouchers

Cite this

@article{130f8400da9047b8832f3d16445c20e1,
title = "Sharp IV bounds on average treatment effects on the treated and other populations under endogeneity and noncompliance",
abstract = "In the presence of an endogenous binary treatment and a valid binary instrument, causal effects are point identified only for the subpopulation of compliers, given that the treatment is monotone in the instrument. With the exception of the entire population, causal inference for further subpopulations has been widely ignored in econometrics. We invoke treatment monotonicity and/or dominance assumptions to derive sharp bounds on the average treatment effects on the treated, as well as on other groups. Furthermore, we use our methods to assess the educational impact of a school voucher program in Colombia and discuss testable implications of our assumptions.",
author = "Martin Huber and Lukas Laffers and Giovanni Mellace",
year = "2017",
doi = "10.1002/jae.2473",
language = "English",
volume = "32",
pages = "56--79",
journal = "Journal of Applied Econometrics",
issn = "0883-7252",
publisher = "JohnWiley & Sons Ltd.",

}

Sharp IV bounds on average treatment effects on the treated and other populations under endogeneity and noncompliance. / Huber, Martin; Laffers, Lukas; Mellace, Giovanni.

In: Journal of Applied Econometrics, Vol. 32, 2017, p. 56-79.

Research output: Contribution to journalJournal articleResearchpeer-review

TY - JOUR

T1 - Sharp IV bounds on average treatment effects on the treated and other populations under endogeneity and noncompliance

AU - Huber, Martin

AU - Laffers, Lukas

AU - Mellace, Giovanni

PY - 2017

Y1 - 2017

N2 - In the presence of an endogenous binary treatment and a valid binary instrument, causal effects are point identified only for the subpopulation of compliers, given that the treatment is monotone in the instrument. With the exception of the entire population, causal inference for further subpopulations has been widely ignored in econometrics. We invoke treatment monotonicity and/or dominance assumptions to derive sharp bounds on the average treatment effects on the treated, as well as on other groups. Furthermore, we use our methods to assess the educational impact of a school voucher program in Colombia and discuss testable implications of our assumptions.

AB - In the presence of an endogenous binary treatment and a valid binary instrument, causal effects are point identified only for the subpopulation of compliers, given that the treatment is monotone in the instrument. With the exception of the entire population, causal inference for further subpopulations has been widely ignored in econometrics. We invoke treatment monotonicity and/or dominance assumptions to derive sharp bounds on the average treatment effects on the treated, as well as on other groups. Furthermore, we use our methods to assess the educational impact of a school voucher program in Colombia and discuss testable implications of our assumptions.

U2 - 10.1002/jae.2473

DO - 10.1002/jae.2473

M3 - Journal article

VL - 32

SP - 56

EP - 79

JO - Journal of Applied Econometrics

JF - Journal of Applied Econometrics

SN - 0883-7252

ER -