Bounding average treatment effects: a linear programming approach

T. Demuynck

doi:10.1016/j.econlet.2015.09.042

Bounding average treatment effects: a linear programming approach

T. Demuynck^*

^*Corresponding author for this work

Microeconomics & Public Economics

Research output: Contribution to journal › Article › Academic › peer-review

Abstract

We show how to obtain bounds on the mean treatment effects by solving a simple linear programming problem. The use of a linear programme is convenient from a practical point of view because it avoids the need to derive closed form solutions. Imposing or omitting monotonicity or concavity restrictions is done by simply adding or removing sets of linear restrictions to the linear programme.

Original language	English
Pages (from-to)	75-77
Number of pages	3
Journal	Economics Letters
Volume	137
DOIs	https://doi.org/10.1016/j.econlet.2015.09.042
Publication status	Published - Dec 2015

Keywords

Treatment effect
Linear programming
Partial identification
PARTIALLY IDENTIFIED PARAMETERS
CONFIDENCE-INTERVALS
RETURNS

Access to Document

10.1016/j.econlet.2015.09.042

Cite this

@article{a4f74785bba14115bf1ca42309166b37,

title = "Bounding average treatment effects: a linear programming approach",

abstract = "We show how to obtain bounds on the mean treatment effects by solving a simple linear programming problem. The use of a linear programme is convenient from a practical point of view because it avoids the need to derive closed form solutions. Imposing or omitting monotonicity or concavity restrictions is done by simply adding or removing sets of linear restrictions to the linear programme.",

keywords = "Treatment effect, Linear programming, Partial identification, PARTIALLY IDENTIFIED PARAMETERS, CONFIDENCE-INTERVALS, RETURNS",

author = "T. Demuynck",

year = "2015",

month = dec,

doi = "10.1016/j.econlet.2015.09.042",

language = "English",

volume = "137",

pages = "75--77",

journal = "Economics Letters",

issn = "0165-1765",

publisher = "Excerpta Medica, Elsevier Science",

}

TY - JOUR

T1 - Bounding average treatment effects: a linear programming approach

AU - Demuynck, T.

PY - 2015/12

Y1 - 2015/12

N2 - We show how to obtain bounds on the mean treatment effects by solving a simple linear programming problem. The use of a linear programme is convenient from a practical point of view because it avoids the need to derive closed form solutions. Imposing or omitting monotonicity or concavity restrictions is done by simply adding or removing sets of linear restrictions to the linear programme.

AB - We show how to obtain bounds on the mean treatment effects by solving a simple linear programming problem. The use of a linear programme is convenient from a practical point of view because it avoids the need to derive closed form solutions. Imposing or omitting monotonicity or concavity restrictions is done by simply adding or removing sets of linear restrictions to the linear programme.

KW - Treatment effect

KW - Linear programming

KW - Partial identification

KW - PARTIALLY IDENTIFIED PARAMETERS

KW - CONFIDENCE-INTERVALS

KW - RETURNS

U2 - 10.1016/j.econlet.2015.09.042

DO - 10.1016/j.econlet.2015.09.042

M3 - Article

SN - 0165-1765

VL - 137

SP - 75

EP - 77

JO - Economics Letters

JF - Economics Letters

ER -