Factor Models in Panels with Cross-sectional Dependence: An Application to the Extended SIPRI Military Expenditure Data

Elisa Cavatorta; Ron P. Smith

doi:10.1080/10242694.2016.1261428

Factor Models in Panels with Cross-sectional Dependence: An Application to the Extended SIPRI Military Expenditure Data

Elisa Cavatorta^*, Ron P. Smith

^*Corresponding author for this work

Birkbeck, University of London

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

21 Citations (Scopus)

205 Downloads (Pure)

Abstract

Strategic interactions between countries, such as arms races, alliances and wider economic and political shocks, can induce strong cross-sectional dependence in panel data models of military expenditure. If the assumption of cross-sectional independence fails, standard panel estimators such as fixed or random effects can lead to misleading inference. This paper shows how to improve estimation of dynamic, heterogenous, panel models of the demand for military expenditure allowing for cross-sectional dependence in errors using two approaches: Principal Components and Common Correlated Effect estimators. Our results show that it is crucial to allow for cross-sectional dependence, that the bulk of the effect is regional and there are large gains in fit by allowing for both dynamics and between country heterogeneity in models of the demand for military expenditures.

Original language	English
Pages (from-to)	437-456
Number of pages	20
Journal	DEFENCE AND PEACE ECONOMICS
Volume	28
Issue number	4
Early online date	16 Jan 2017
DOIs	https://doi.org/10.1080/10242694.2016.1261428
Publication status	Published - 4 Jul 2017

Keywords

factor models
Military expenditures
panel data

Access to Document

10.1080/10242694.2016.1261428

Factor Models in Panels_CAVATORTA_Publishedonline16January2017_GREEN AAM
This is an Accepted Manuscript of an article published by Taylor & Francis in Defence and Peace Economics on 16/01/17, available online: http://www.tandfonline.com/doi/full/10.1080/10242694.2016.1261428
Accepted author manuscript, 634 KBLicence: Other

Cite this

@article{de3f267e0a744ba8a908b60aafedf990,

title = "Factor Models in Panels with Cross-sectional Dependence: An Application to the Extended SIPRI Military Expenditure Data",

abstract = "Strategic interactions between countries, such as arms races, alliances and wider economic and political shocks, can induce strong cross-sectional dependence in panel data models of military expenditure. If the assumption of cross-sectional independence fails, standard panel estimators such as fixed or random effects can lead to misleading inference. This paper shows how to improve estimation of dynamic, heterogenous, panel models of the demand for military expenditure allowing for cross-sectional dependence in errors using two approaches: Principal Components and Common Correlated Effect estimators. Our results show that it is crucial to allow for cross-sectional dependence, that the bulk of the effect is regional and there are large gains in fit by allowing for both dynamics and between country heterogeneity in models of the demand for military expenditures.",

keywords = "factor models, Military expenditures, panel data",

author = "Elisa Cavatorta and Smith, {Ron P.}",

year = "2017",

month = jul,

day = "4",

doi = "10.1080/10242694.2016.1261428",

language = "English",

volume = "28",

pages = "437--456",

journal = "DEFENCE AND PEACE ECONOMICS",

issn = "1024-2694",

publisher = "Routledge",

number = "4",

}

TY - JOUR

T1 - Factor Models in Panels with Cross-sectional Dependence

T2 - An Application to the Extended SIPRI Military Expenditure Data

AU - Cavatorta, Elisa

AU - Smith, Ron P.

PY - 2017/7/4

Y1 - 2017/7/4

N2 - Strategic interactions between countries, such as arms races, alliances and wider economic and political shocks, can induce strong cross-sectional dependence in panel data models of military expenditure. If the assumption of cross-sectional independence fails, standard panel estimators such as fixed or random effects can lead to misleading inference. This paper shows how to improve estimation of dynamic, heterogenous, panel models of the demand for military expenditure allowing for cross-sectional dependence in errors using two approaches: Principal Components and Common Correlated Effect estimators. Our results show that it is crucial to allow for cross-sectional dependence, that the bulk of the effect is regional and there are large gains in fit by allowing for both dynamics and between country heterogeneity in models of the demand for military expenditures.

AB - Strategic interactions between countries, such as arms races, alliances and wider economic and political shocks, can induce strong cross-sectional dependence in panel data models of military expenditure. If the assumption of cross-sectional independence fails, standard panel estimators such as fixed or random effects can lead to misleading inference. This paper shows how to improve estimation of dynamic, heterogenous, panel models of the demand for military expenditure allowing for cross-sectional dependence in errors using two approaches: Principal Components and Common Correlated Effect estimators. Our results show that it is crucial to allow for cross-sectional dependence, that the bulk of the effect is regional and there are large gains in fit by allowing for both dynamics and between country heterogeneity in models of the demand for military expenditures.

KW - factor models

KW - Military expenditures

KW - panel data

UR - http://www.scopus.com/inward/record.url?scp=85009511144&partnerID=8YFLogxK

U2 - 10.1080/10242694.2016.1261428

DO - 10.1080/10242694.2016.1261428

M3 - Article

AN - SCOPUS:85009511144

SN - 1024-2694

VL - 28

SP - 437

EP - 456

JO - DEFENCE AND PEACE ECONOMICS

JF - DEFENCE AND PEACE ECONOMICS

IS - 4

ER -

Factor Models in Panels with Cross-sectional Dependence: An Application to the Extended SIPRI Military Expenditure Data

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this