Forecasting ARMA models: a comparative study of information criteria focusing on MDIC

Panagiotis Mantalos; K. Mattheou; A. Karagrigoriou

doi:10.1080/00949650802464137

Forecasting ARMA models: a comparative study of information criteria focusing on MDIC

Panagiotis Mantalos, K. Mattheou, A. Karagrigoriou

Department of Statistics

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

Abstract

This paper deals with the implementation of model selection criteria to data generated by ARMA processes. The recently introduced modified divergence information criterion is used and compared with traditional selection criteria like the Akaike information criterion (AIC) and the Schwarz information criterion (SIC). The appropriateness of the selected model is tested for one- and five-step ahead predictions with the use of the normalized mean squared forecast errors (NMSFE).

Original language	English
Pages (from-to)	61-73
Journal	Journal of Statistical Computation and Simulation
Volume	80
Issue number	1-2
DOIs	https://doi.org/10.1080/00949650802464137
Publication status	Published - 2010

Subject classification (UKÄ)

Probability Theory and Statistics

Free keywords

NMSFE
MDIC
model selection
ARMA process
information criterion

Access to Document

10.1080/00949650802464137

Cite this

@article{2043e8b2908145ff8c799680a2b05a44,

title = "Forecasting ARMA models: a comparative study of information criteria focusing on MDIC",

abstract = "This paper deals with the implementation of model selection criteria to data generated by ARMA processes. The recently introduced modified divergence information criterion is used and compared with traditional selection criteria like the Akaike information criterion (AIC) and the Schwarz information criterion (SIC). The appropriateness of the selected model is tested for one- and five-step ahead predictions with the use of the normalized mean squared forecast errors (NMSFE).",

keywords = "NMSFE, MDIC, model selection, ARMA process, information criterion",

author = "Panagiotis Mantalos and K. Mattheou and A. Karagrigoriou",

year = "2010",

doi = "10.1080/00949650802464137",

language = "English",

volume = "80",

pages = "61--73",

journal = "Journal of Statistical Computation and Simulation",

issn = "1563-5163",

publisher = "Taylor & Francis",

number = "1-2",

}

TY - JOUR

T1 - Forecasting ARMA models: a comparative study of information criteria focusing on MDIC

AU - Mantalos, Panagiotis

AU - Mattheou, K.

AU - Karagrigoriou, A.

PY - 2010

Y1 - 2010

N2 - This paper deals with the implementation of model selection criteria to data generated by ARMA processes. The recently introduced modified divergence information criterion is used and compared with traditional selection criteria like the Akaike information criterion (AIC) and the Schwarz information criterion (SIC). The appropriateness of the selected model is tested for one- and five-step ahead predictions with the use of the normalized mean squared forecast errors (NMSFE).

AB - This paper deals with the implementation of model selection criteria to data generated by ARMA processes. The recently introduced modified divergence information criterion is used and compared with traditional selection criteria like the Akaike information criterion (AIC) and the Schwarz information criterion (SIC). The appropriateness of the selected model is tested for one- and five-step ahead predictions with the use of the normalized mean squared forecast errors (NMSFE).

KW - NMSFE

KW - MDIC

KW - model selection

KW - ARMA process

KW - information criterion

U2 - 10.1080/00949650802464137

DO - 10.1080/00949650802464137

M3 - Article

SN - 1563-5163

VL - 80

SP - 61

EP - 73

JO - Journal of Statistical Computation and Simulation

JF - Journal of Statistical Computation and Simulation

IS - 1-2

ER -

Forecasting ARMA models: a comparative study of information criteria focusing on MDIC

Abstract

Subject classification (UKÄ)

Free keywords

Access to Document

Fingerprint

Cite this