Dynamic foreign policy behavior

Matthew J. Lebo, Will H. Moore

Research output: Contribution to journalArticle

13 Citations (Scopus)

Abstract

How best to classify event counts of directed dyadic foreign policy behavior and how best to model them are points of disagreement among researchers. Should such series be modeled as unit roots ("perfect" memory) or as stationary ("short" memory)? It is demonstrated that the dichotomous choice between unit root (I(1)) and level stationarity (I(0)) is overly restrictive. The intermediate (and more general) possibility of fractional integration (0 <I <1), a concept proven useful in studies of aggregate opinion, is applied. Results show that fractional integration is extremely common and that error correction mechanisms (ECMs) can still be appropriate in the absence of unit-root series. Fractional ECMs are used in action-reaction models of bilateral relationships to demonstrate this. Given the frequency of fractional integration, its flexibility, and the problems encountered when ignoring it, scholars should incorporate fractional integration techniques into their models.

Original languageEnglish (US)
Pages (from-to)13-32
Number of pages20
JournalJournal of Conflict Resolution
Volume47
Issue number1
DOIs
StatePublished - Feb 2003
Externally publishedYes

Fingerprint

foreign policy
flexibility
event
Foreign policy
Fractional integration
Unit root
Error correction mechanism

Keywords

  • Action-reaction
  • ARFIMA
  • Error correction mechanisms
  • Foreign policy
  • Fractional integration

ASJC Scopus subject areas

  • Political Science and International Relations
  • Sociology and Political Science
  • Business, Management and Accounting(all)

Cite this

Dynamic foreign policy behavior. / Lebo, Matthew J.; Moore, Will H.

In: Journal of Conflict Resolution, Vol. 47, No. 1, 02.2003, p. 13-32.

Research output: Contribution to journalArticle

Lebo, Matthew J. ; Moore, Will H. / Dynamic foreign policy behavior. In: Journal of Conflict Resolution. 2003 ; Vol. 47, No. 1. pp. 13-32.
@article{4bb68142fa714a6b83dcd4024905b537,
title = "Dynamic foreign policy behavior",
abstract = "How best to classify event counts of directed dyadic foreign policy behavior and how best to model them are points of disagreement among researchers. Should such series be modeled as unit roots ({"}perfect{"} memory) or as stationary ({"}short{"} memory)? It is demonstrated that the dichotomous choice between unit root (I(1)) and level stationarity (I(0)) is overly restrictive. The intermediate (and more general) possibility of fractional integration (0 <I <1), a concept proven useful in studies of aggregate opinion, is applied. Results show that fractional integration is extremely common and that error correction mechanisms (ECMs) can still be appropriate in the absence of unit-root series. Fractional ECMs are used in action-reaction models of bilateral relationships to demonstrate this. Given the frequency of fractional integration, its flexibility, and the problems encountered when ignoring it, scholars should incorporate fractional integration techniques into their models.",
keywords = "Action-reaction, ARFIMA, Error correction mechanisms, Foreign policy, Fractional integration",
author = "Lebo, {Matthew J.} and Moore, {Will H.}",
year = "2003",
month = "2",
doi = "10.1177/0022002702239509",
language = "English (US)",
volume = "47",
pages = "13--32",
journal = "Journal of Conflict Resolution",
issn = "0022-0027",
publisher = "SAGE Publications Inc.",
number = "1",

}

TY - JOUR

T1 - Dynamic foreign policy behavior

AU - Lebo, Matthew J.

AU - Moore, Will H.

PY - 2003/2

Y1 - 2003/2

N2 - How best to classify event counts of directed dyadic foreign policy behavior and how best to model them are points of disagreement among researchers. Should such series be modeled as unit roots ("perfect" memory) or as stationary ("short" memory)? It is demonstrated that the dichotomous choice between unit root (I(1)) and level stationarity (I(0)) is overly restrictive. The intermediate (and more general) possibility of fractional integration (0 <I <1), a concept proven useful in studies of aggregate opinion, is applied. Results show that fractional integration is extremely common and that error correction mechanisms (ECMs) can still be appropriate in the absence of unit-root series. Fractional ECMs are used in action-reaction models of bilateral relationships to demonstrate this. Given the frequency of fractional integration, its flexibility, and the problems encountered when ignoring it, scholars should incorporate fractional integration techniques into their models.

AB - How best to classify event counts of directed dyadic foreign policy behavior and how best to model them are points of disagreement among researchers. Should such series be modeled as unit roots ("perfect" memory) or as stationary ("short" memory)? It is demonstrated that the dichotomous choice between unit root (I(1)) and level stationarity (I(0)) is overly restrictive. The intermediate (and more general) possibility of fractional integration (0 <I <1), a concept proven useful in studies of aggregate opinion, is applied. Results show that fractional integration is extremely common and that error correction mechanisms (ECMs) can still be appropriate in the absence of unit-root series. Fractional ECMs are used in action-reaction models of bilateral relationships to demonstrate this. Given the frequency of fractional integration, its flexibility, and the problems encountered when ignoring it, scholars should incorporate fractional integration techniques into their models.

KW - Action-reaction

KW - ARFIMA

KW - Error correction mechanisms

KW - Foreign policy

KW - Fractional integration

UR - http://www.scopus.com/inward/record.url?scp=0037281711&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0037281711&partnerID=8YFLogxK

U2 - 10.1177/0022002702239509

DO - 10.1177/0022002702239509

M3 - Article

AN - SCOPUS:0037281711

VL - 47

SP - 13

EP - 32

JO - Journal of Conflict Resolution

JF - Journal of Conflict Resolution

SN - 0022-0027

IS - 1

ER -