Distance and prediction error variance constraints for ARMA model portfolios

Timothy Chenoweth, Karen Dowling, Robert Hubata, Robert St Louis

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Poskitt and Tremayne 74 (1987) present a posterior odds ratio (R) portfolio selection strategy for ARMA models. This paper makes the range of prediction error variances that are implicit in R more explicit. Model closeness is quantified using a distance function in a Hilbert space. The relationship between distance and the posterior odds ratio is demonstrated. This provides a distance interpretation of the posterior odds ratio. The distance function also makes it possible to develop a prediction error variance (p.e.v.) criterion for identifying models to include in an ARMA model portfolio. A simulation experiment shows that the p.e.v. criterion provides forecasters with both a measure for assessing the likelihood that the models in an ARMA model portfolio yield practically equivalent forecasts, and a measure for assessing the usefulness of alternative criteria for identifying the order of an ARMA model.

Original languageEnglish (US)
Pages (from-to)41-52
Number of pages12
JournalInternational Journal of Forecasting
Volume20
Issue number1
DOIs
StatePublished - Jan 2004

Fingerprint

ARMA model
Prediction error
Odds ratio
Distance function
Closeness
Simulation experiment
Hilbert space
Portfolio selection
Usefulness

Keywords

  • Distance
  • Information criteria
  • Misspecification error
  • Order determination
  • Posterior odds ratio
  • Prediction error variance

ASJC Scopus subject areas

  • Business and International Management

Cite this

Distance and prediction error variance constraints for ARMA model portfolios. / Chenoweth, Timothy; Dowling, Karen; Hubata, Robert; St Louis, Robert.

In: International Journal of Forecasting, Vol. 20, No. 1, 01.2004, p. 41-52.

Research output: Contribution to journalArticle

Chenoweth, Timothy ; Dowling, Karen ; Hubata, Robert ; St Louis, Robert. / Distance and prediction error variance constraints for ARMA model portfolios. In: International Journal of Forecasting. 2004 ; Vol. 20, No. 1. pp. 41-52.
@article{9f05c9becb364496a5bb897de51df91c,
title = "Distance and prediction error variance constraints for ARMA model portfolios",
abstract = "Poskitt and Tremayne 74 (1987) present a posterior odds ratio (R) portfolio selection strategy for ARMA models. This paper makes the range of prediction error variances that are implicit in R more explicit. Model closeness is quantified using a distance function in a Hilbert space. The relationship between distance and the posterior odds ratio is demonstrated. This provides a distance interpretation of the posterior odds ratio. The distance function also makes it possible to develop a prediction error variance (p.e.v.) criterion for identifying models to include in an ARMA model portfolio. A simulation experiment shows that the p.e.v. criterion provides forecasters with both a measure for assessing the likelihood that the models in an ARMA model portfolio yield practically equivalent forecasts, and a measure for assessing the usefulness of alternative criteria for identifying the order of an ARMA model.",
keywords = "Distance, Information criteria, Misspecification error, Order determination, Posterior odds ratio, Prediction error variance",
author = "Timothy Chenoweth and Karen Dowling and Robert Hubata and {St Louis}, Robert",
year = "2004",
month = "1",
doi = "10.1016/S0169-2070(03)00006-2",
language = "English (US)",
volume = "20",
pages = "41--52",
journal = "International Journal of Forecasting",
issn = "0169-2070",
publisher = "Elsevier",
number = "1",

}

TY - JOUR

T1 - Distance and prediction error variance constraints for ARMA model portfolios

AU - Chenoweth, Timothy

AU - Dowling, Karen

AU - Hubata, Robert

AU - St Louis, Robert

PY - 2004/1

Y1 - 2004/1

N2 - Poskitt and Tremayne 74 (1987) present a posterior odds ratio (R) portfolio selection strategy for ARMA models. This paper makes the range of prediction error variances that are implicit in R more explicit. Model closeness is quantified using a distance function in a Hilbert space. The relationship between distance and the posterior odds ratio is demonstrated. This provides a distance interpretation of the posterior odds ratio. The distance function also makes it possible to develop a prediction error variance (p.e.v.) criterion for identifying models to include in an ARMA model portfolio. A simulation experiment shows that the p.e.v. criterion provides forecasters with both a measure for assessing the likelihood that the models in an ARMA model portfolio yield practically equivalent forecasts, and a measure for assessing the usefulness of alternative criteria for identifying the order of an ARMA model.

AB - Poskitt and Tremayne 74 (1987) present a posterior odds ratio (R) portfolio selection strategy for ARMA models. This paper makes the range of prediction error variances that are implicit in R more explicit. Model closeness is quantified using a distance function in a Hilbert space. The relationship between distance and the posterior odds ratio is demonstrated. This provides a distance interpretation of the posterior odds ratio. The distance function also makes it possible to develop a prediction error variance (p.e.v.) criterion for identifying models to include in an ARMA model portfolio. A simulation experiment shows that the p.e.v. criterion provides forecasters with both a measure for assessing the likelihood that the models in an ARMA model portfolio yield practically equivalent forecasts, and a measure for assessing the usefulness of alternative criteria for identifying the order of an ARMA model.

KW - Distance

KW - Information criteria

KW - Misspecification error

KW - Order determination

KW - Posterior odds ratio

KW - Prediction error variance

UR - http://www.scopus.com/inward/record.url?scp=0742289112&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0742289112&partnerID=8YFLogxK

U2 - 10.1016/S0169-2070(03)00006-2

DO - 10.1016/S0169-2070(03)00006-2

M3 - Article

AN - SCOPUS:0742289112

VL - 20

SP - 41

EP - 52

JO - International Journal of Forecasting

JF - International Journal of Forecasting

SN - 0169-2070

IS - 1

ER -