Econometric Analysis of Panel Data Models with Multifactor Error Structures

Hande Karabiyik, Franz C. Palm, Jean Pierre Urbain

Research output: Contribution to JournalReview articleAcademicpeer-review

Abstract

Economic panel data often exhibit cross-sectional dependence, even after conditioning on appropriate explanatory variables. Two approaches to modeling cross-sectional dependence in economic panel data are often used: the spatial dependence approach, which explains cross-sectional dependence in terms of distance among units, and the residual multifactor approach, which explains cross-sectional dependence by common factors that affect individuals to a different extent. This article reviews the theory on estimation and statistical inference for stationary and nonstationary panel data with cross-sectional dependence, particularly for models with a multifactor error structure. Tests and diagnostics for testing for unit roots, slope homogeneity, cointegration, and the number of factors are provided. We discuss issues such as estimating common factors, dealing with parameter plethora in practice, testing for structural stability and nonlinearity, and dealing with model and parameter uncertainty. Finally, we address issues related to the use of these economic panel models.

Original languageEnglish
Pages (from-to)495-522
Number of pages28
JournalAnnual Review of Economics
Volume11
DOIs
Publication statusPublished - 2 Aug 2019

Fingerprint

Multi-factor
Cross-sectional dependence
Econometric analysis
Economics
Testing
Common factors
Panel data
Unit root
Modeling
Spatial dependence
Nonlinearity
Conditioning
Panel model
Statistical inference
Cointegration
Factors
Model uncertainty
Diagnostics
Non-stationary panel data
Homogeneity

Keywords

  • common correlated effects
  • cross-sectional dependence
  • factor-augmented panel regression
  • nonstationary panels
  • panel data
  • principal components
  • stationary panels

Cite this

Karabiyik, Hande ; Palm, Franz C. ; Urbain, Jean Pierre. / Econometric Analysis of Panel Data Models with Multifactor Error Structures. In: Annual Review of Economics. 2019 ; Vol. 11. pp. 495-522.
@article{7231b7785dec43ab897c261711d2406e,
title = "Econometric Analysis of Panel Data Models with Multifactor Error Structures",
abstract = "Economic panel data often exhibit cross-sectional dependence, even after conditioning on appropriate explanatory variables. Two approaches to modeling cross-sectional dependence in economic panel data are often used: the spatial dependence approach, which explains cross-sectional dependence in terms of distance among units, and the residual multifactor approach, which explains cross-sectional dependence by common factors that affect individuals to a different extent. This article reviews the theory on estimation and statistical inference for stationary and nonstationary panel data with cross-sectional dependence, particularly for models with a multifactor error structure. Tests and diagnostics for testing for unit roots, slope homogeneity, cointegration, and the number of factors are provided. We discuss issues such as estimating common factors, dealing with parameter plethora in practice, testing for structural stability and nonlinearity, and dealing with model and parameter uncertainty. Finally, we address issues related to the use of these economic panel models.",
keywords = "common correlated effects, cross-sectional dependence, factor-augmented panel regression, nonstationary panels, panel data, principal components, stationary panels",
author = "Hande Karabiyik and Palm, {Franz C.} and Urbain, {Jean Pierre}",
year = "2019",
month = "8",
day = "2",
doi = "10.1146/annurev-economics-063016-104338",
language = "English",
volume = "11",
pages = "495--522",
journal = "Annual Review of Economics",
issn = "1941-1383",
publisher = "Annual Reviews",

}

Econometric Analysis of Panel Data Models with Multifactor Error Structures. / Karabiyik, Hande; Palm, Franz C.; Urbain, Jean Pierre.

In: Annual Review of Economics, Vol. 11, 02.08.2019, p. 495-522.

Research output: Contribution to JournalReview articleAcademicpeer-review

TY - JOUR

T1 - Econometric Analysis of Panel Data Models with Multifactor Error Structures

AU - Karabiyik, Hande

AU - Palm, Franz C.

AU - Urbain, Jean Pierre

PY - 2019/8/2

Y1 - 2019/8/2

N2 - Economic panel data often exhibit cross-sectional dependence, even after conditioning on appropriate explanatory variables. Two approaches to modeling cross-sectional dependence in economic panel data are often used: the spatial dependence approach, which explains cross-sectional dependence in terms of distance among units, and the residual multifactor approach, which explains cross-sectional dependence by common factors that affect individuals to a different extent. This article reviews the theory on estimation and statistical inference for stationary and nonstationary panel data with cross-sectional dependence, particularly for models with a multifactor error structure. Tests and diagnostics for testing for unit roots, slope homogeneity, cointegration, and the number of factors are provided. We discuss issues such as estimating common factors, dealing with parameter plethora in practice, testing for structural stability and nonlinearity, and dealing with model and parameter uncertainty. Finally, we address issues related to the use of these economic panel models.

AB - Economic panel data often exhibit cross-sectional dependence, even after conditioning on appropriate explanatory variables. Two approaches to modeling cross-sectional dependence in economic panel data are often used: the spatial dependence approach, which explains cross-sectional dependence in terms of distance among units, and the residual multifactor approach, which explains cross-sectional dependence by common factors that affect individuals to a different extent. This article reviews the theory on estimation and statistical inference for stationary and nonstationary panel data with cross-sectional dependence, particularly for models with a multifactor error structure. Tests and diagnostics for testing for unit roots, slope homogeneity, cointegration, and the number of factors are provided. We discuss issues such as estimating common factors, dealing with parameter plethora in practice, testing for structural stability and nonlinearity, and dealing with model and parameter uncertainty. Finally, we address issues related to the use of these economic panel models.

KW - common correlated effects

KW - cross-sectional dependence

KW - factor-augmented panel regression

KW - nonstationary panels

KW - panel data

KW - principal components

KW - stationary panels

UR - http://www.scopus.com/inward/record.url?scp=85071615787&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85071615787&partnerID=8YFLogxK

U2 - 10.1146/annurev-economics-063016-104338

DO - 10.1146/annurev-economics-063016-104338

M3 - Review article

VL - 11

SP - 495

EP - 522

JO - Annual Review of Economics

JF - Annual Review of Economics

SN - 1941-1383

ER -