Combinatorial approach to inference in partially identified incomplete structural models

Marc Henry, Romuald Méango, Maurice Queyranne

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

We propose a computationally feasible inference method in finite games of complete information. Galichon and Henry, 2011 and Beresteanu, Molchanov, and Molinari, 2011 show that the empirical content in such models is characterized by a collection of moment inequalities whose number increases exponentially with the number of discrete outcomes. We propose an equivalent characterization based on classical combinatorial optimization methods that allows the construction of confidence regions with an efficient bootstrap procedure that runs in linear computing time. The method can be applied to the empirical analysis of cooperative and noncooperative games, instrumental variable models of discrete choice, and revealed preference analysis. We propose an application to the determinants of long term elderly care choices.

Original languageEnglish (US)
Pages (from-to)499-529
Number of pages31
JournalQuantitative Economics
Volume6
Issue number2
DOIs
StatePublished - Jul 1 2015

Fingerprint

Structural model
Inference
Combinatorial optimization
Preference analysis
Complete information
Revealed preference
Instrumental variables
Elderly care
Non-cooperative game
Empirical analysis
Discrete choice
Cooperative game
Bootstrap
Confidence region
Moment inequalities

All Science Journal Classification (ASJC) codes

  • Economics and Econometrics

Cite this

Henry, Marc ; Méango, Romuald ; Queyranne, Maurice. / Combinatorial approach to inference in partially identified incomplete structural models. In: Quantitative Economics. 2015 ; Vol. 6, No. 2. pp. 499-529.
@article{a878df145ddc4cfda4943965616239b9,
title = "Combinatorial approach to inference in partially identified incomplete structural models",
abstract = "We propose a computationally feasible inference method in finite games of complete information. Galichon and Henry, 2011 and Beresteanu, Molchanov, and Molinari, 2011 show that the empirical content in such models is characterized by a collection of moment inequalities whose number increases exponentially with the number of discrete outcomes. We propose an equivalent characterization based on classical combinatorial optimization methods that allows the construction of confidence regions with an efficient bootstrap procedure that runs in linear computing time. The method can be applied to the empirical analysis of cooperative and noncooperative games, instrumental variable models of discrete choice, and revealed preference analysis. We propose an application to the determinants of long term elderly care choices.",
author = "Marc Henry and Romuald M{\'e}ango and Maurice Queyranne",
year = "2015",
month = "7",
day = "1",
doi = "10.3982/QE377",
language = "English (US)",
volume = "6",
pages = "499--529",
journal = "Quantitative Economics",
issn = "1759-7323",
publisher = "The Economic Society",
number = "2",

}

Combinatorial approach to inference in partially identified incomplete structural models. / Henry, Marc; Méango, Romuald; Queyranne, Maurice.

In: Quantitative Economics, Vol. 6, No. 2, 01.07.2015, p. 499-529.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Combinatorial approach to inference in partially identified incomplete structural models

AU - Henry, Marc

AU - Méango, Romuald

AU - Queyranne, Maurice

PY - 2015/7/1

Y1 - 2015/7/1

N2 - We propose a computationally feasible inference method in finite games of complete information. Galichon and Henry, 2011 and Beresteanu, Molchanov, and Molinari, 2011 show that the empirical content in such models is characterized by a collection of moment inequalities whose number increases exponentially with the number of discrete outcomes. We propose an equivalent characterization based on classical combinatorial optimization methods that allows the construction of confidence regions with an efficient bootstrap procedure that runs in linear computing time. The method can be applied to the empirical analysis of cooperative and noncooperative games, instrumental variable models of discrete choice, and revealed preference analysis. We propose an application to the determinants of long term elderly care choices.

AB - We propose a computationally feasible inference method in finite games of complete information. Galichon and Henry, 2011 and Beresteanu, Molchanov, and Molinari, 2011 show that the empirical content in such models is characterized by a collection of moment inequalities whose number increases exponentially with the number of discrete outcomes. We propose an equivalent characterization based on classical combinatorial optimization methods that allows the construction of confidence regions with an efficient bootstrap procedure that runs in linear computing time. The method can be applied to the empirical analysis of cooperative and noncooperative games, instrumental variable models of discrete choice, and revealed preference analysis. We propose an application to the determinants of long term elderly care choices.

UR - http://www.scopus.com/inward/record.url?scp=84938560956&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84938560956&partnerID=8YFLogxK

U2 - 10.3982/QE377

DO - 10.3982/QE377

M3 - Article

AN - SCOPUS:84938560956

VL - 6

SP - 499

EP - 529

JO - Quantitative Economics

JF - Quantitative Economics

SN - 1759-7323

IS - 2

ER -