Partial identification in binary response models with nonignorable nonresponses

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

This study investigates the identification of parameters in semiparametric binary response models of the form y=1(x'β+v+ε>0) when there are nonignorable nonresponses. We propose an estimation procedure for the identified set, the set of parameters that are observationally indistinguishable from the true value β, based on the special regressor approach of Lewbel (2000). We show that the estimator for the identified set is consistent in the Hausdorff metric.

Original languageEnglish
Pages (from-to)74-78
Number of pages5
JournalEconomics Letters
Volume121
Issue number1
DOIs
Publication statusPublished - 2013
Externally publishedYes

Fingerprint

Binary response model
Partial identification
Non-response
Estimator

Keywords

  • Nonignorable nonresponses
  • Partial identification
  • Semiparametric binary response models
  • Special regressor approach

ASJC Scopus subject areas

  • Economics and Econometrics
  • Finance

Cite this

Partial identification in binary response models with nonignorable nonresponses. / Hoshino, Tadao.

In: Economics Letters, Vol. 121, No. 1, 2013, p. 74-78.

Research output: Contribution to journalArticle

@article{b0bc7aba5c944c97ba568cbf2d321302,
title = "Partial identification in binary response models with nonignorable nonresponses",
abstract = "This study investigates the identification of parameters in semiparametric binary response models of the form y=1(x'β+v+ε>0) when there are nonignorable nonresponses. We propose an estimation procedure for the identified set, the set of parameters that are observationally indistinguishable from the true value β, based on the special regressor approach of Lewbel (2000). We show that the estimator for the identified set is consistent in the Hausdorff metric.",
keywords = "Nonignorable nonresponses, Partial identification, Semiparametric binary response models, Special regressor approach",
author = "Tadao Hoshino",
year = "2013",
doi = "10.1016/j.econlet.2013.07.009",
language = "English",
volume = "121",
pages = "74--78",
journal = "Economics Letters",
issn = "0165-1765",
publisher = "Elsevier",
number = "1",

}

TY - JOUR

T1 - Partial identification in binary response models with nonignorable nonresponses

AU - Hoshino, Tadao

PY - 2013

Y1 - 2013

N2 - This study investigates the identification of parameters in semiparametric binary response models of the form y=1(x'β+v+ε>0) when there are nonignorable nonresponses. We propose an estimation procedure for the identified set, the set of parameters that are observationally indistinguishable from the true value β, based on the special regressor approach of Lewbel (2000). We show that the estimator for the identified set is consistent in the Hausdorff metric.

AB - This study investigates the identification of parameters in semiparametric binary response models of the form y=1(x'β+v+ε>0) when there are nonignorable nonresponses. We propose an estimation procedure for the identified set, the set of parameters that are observationally indistinguishable from the true value β, based on the special regressor approach of Lewbel (2000). We show that the estimator for the identified set is consistent in the Hausdorff metric.

KW - Nonignorable nonresponses

KW - Partial identification

KW - Semiparametric binary response models

KW - Special regressor approach

UR - http://www.scopus.com/inward/record.url?scp=84882799536&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84882799536&partnerID=8YFLogxK

U2 - 10.1016/j.econlet.2013.07.009

DO - 10.1016/j.econlet.2013.07.009

M3 - Article

AN - SCOPUS:84882799536

VL - 121

SP - 74

EP - 78

JO - Economics Letters

JF - Economics Letters

SN - 0165-1765

IS - 1

ER -