Estimation of Panel Data Regression Models with Two-Sided Censoring or Truncation

Sule Alan; Bo E. Honore; Luojia Hu; Søren Leth-Petersen

doi:10.1515/jem-2012-0012

Estimation of Panel Data Regression Models with Two-Sided Censoring or Truncation

Sule Alan, Bo E. Honore, Luojia Hu, Søren Leth-Petersen

Økonomisk Institut

15 Citationer (Scopus)

Abstract

This paper constructs estimators for panel data regression models with individual speci…fic heterogeneity and two–sided censoring and truncation. Following Powell (1986) the estimation strategy is based on moment conditions constructed from re–censored or re–truncated residuals. While these moment conditions do not identify the parameter of interest, they can be used to motivate objective functions that do. We apply one of the estimators to study the e¤ect of a Danish tax reform on household portfolio choice. The idea behind the estimators can also be used in a cross sectional setting.

Originalsprog	Engelsk
Tidsskrift	Journal of Econometric Methods
Vol/bind	3
Udgave nummer	1
Sider (fra-til)	1-20
Antal sider	20
ISSN	2156-6674
DOI	https://doi.org/10.1515/jem-2012-0012
Status	Udgivet - 2021

Emneord

Det Samfundsvidenskabelige Fakultet
censored regression
panel data
truncated regression

Adgang til dokumentet

10.1515/jem-2012-0012

Citationsformater

@article{1951c6894a0547dba97a55e95cf7c16c,

title = "Estimation of Panel Data Regression Models with Two-Sided Censoring or Truncation",

abstract = "This paper constructs estimators for panel data regression models with individual specific heterogeneity and two-sided censoring and truncation. Following Powell the estimation strategy is based on moment conditions constructed from re-censored or re-truncated residuals. While these moment conditions do not identify the parameter of interest, they can be used to motivate objective functions that do. We apply one of the estimators to study the effect of a Danish tax reform on household portfolio choice. The idea behind the estimators can also be used in a cross sectional setting.",

keywords = "Faculty of Social Sciences, censored regression , panel data, truncated regression, censored regression, panel data, truncated regression",

author = "Sule Alan and Honore, {Bo E.} and Luojia Hu and S{\o}ren Leth-Petersen",

note = "JEL Code: C20; C23; C24",

year = "2021",

doi = "10.1515/jem-2012-0012",

language = "English",

volume = "3",

pages = "1--20",

journal = "Journal of Econometric Methods",

issn = "2156-6674",

publisher = "Walterde Gruyter GmbH",

number = "1",

}

TY - JOUR

T1 - Estimation of Panel Data Regression Models with Two-Sided Censoring or Truncation

AU - Alan, Sule

AU - Honore, Bo E.

AU - Hu, Luojia

AU - Leth-Petersen, Søren

N1 - JEL Code: C20; C23; C24

PY - 2021

Y1 - 2021

N2 - This paper constructs estimators for panel data regression models with individual specific heterogeneity and two-sided censoring and truncation. Following Powell the estimation strategy is based on moment conditions constructed from re-censored or re-truncated residuals. While these moment conditions do not identify the parameter of interest, they can be used to motivate objective functions that do. We apply one of the estimators to study the effect of a Danish tax reform on household portfolio choice. The idea behind the estimators can also be used in a cross sectional setting.

AB - This paper constructs estimators for panel data regression models with individual specific heterogeneity and two-sided censoring and truncation. Following Powell the estimation strategy is based on moment conditions constructed from re-censored or re-truncated residuals. While these moment conditions do not identify the parameter of interest, they can be used to motivate objective functions that do. We apply one of the estimators to study the effect of a Danish tax reform on household portfolio choice. The idea behind the estimators can also be used in a cross sectional setting.

KW - Faculty of Social Sciences

KW - censored regression

KW - panel data

KW - truncated regression

KW - censored regression

KW - panel data

KW - truncated regression

U2 - 10.1515/jem-2012-0012

DO - 10.1515/jem-2012-0012

M3 - Journal article

SN - 2156-6674

VL - 3

SP - 1

EP - 20

JO - Journal of Econometric Methods

JF - Journal of Econometric Methods

IS - 1

ER -

Estimation of Panel Data Regression Models with Two-Sided Censoring or Truncation

Abstract

Emneord

Adgang til dokumentet

Fingeraftryk

Citationsformater