An evaluation of volatility forecasting techniques

Timothy J. Brailsford, Robert W. Faff

Research output: Contribution to journalArticleResearchpeer-review

193 Citations (Scopus)

Abstract

The existing literature contains conflicting evidence regarding the relative quality of stock market volatility forecasts. Evidence can be found supporting the superiority of relatively complex models (including ARCH class models), while there is also evidence supporting the superiority of more simple alternatives. These inconsistencies are of particular concern because of the use of, and reliance on, volatility forecasts in key economic decision-making and analysis, and in asset/option pricing. This paper employs daily Australian data to examine this issue. The results suggest that the ARCH class of models and a simple regression model provide superior forecasts of volatility. However, the various model rankings are shown to be sensitive to the error statistic used to assess the accuracy of the forecasts. Nevertheless, a clear message is that volatility forecasting is a notoriously difficult task.

Original languageEnglish
Pages (from-to)419-438
Number of pages20
JournalJournal of Banking and Finance
Volume20
Issue number3
DOIs
Publication statusPublished - Apr 1996
Externally publishedYes

Fingerprint

Volatility forecasting
Evaluation
Autoregressive conditional heteroscedasticity
Volatility forecasts
Decision making
Economics
Stock market volatility
Decision analysis
Ranking
Regression model
Statistics
Inconsistency
Option pricing
Assets

Cite this

Brailsford, Timothy J. ; Faff, Robert W. / An evaluation of volatility forecasting techniques. In: Journal of Banking and Finance. 1996 ; Vol. 20, No. 3. pp. 419-438.
@article{7a32483f15d24f618df7ced6e0b3ed79,
title = "An evaluation of volatility forecasting techniques",
abstract = "The existing literature contains conflicting evidence regarding the relative quality of stock market volatility forecasts. Evidence can be found supporting the superiority of relatively complex models (including ARCH class models), while there is also evidence supporting the superiority of more simple alternatives. These inconsistencies are of particular concern because of the use of, and reliance on, volatility forecasts in key economic decision-making and analysis, and in asset/option pricing. This paper employs daily Australian data to examine this issue. The results suggest that the ARCH class of models and a simple regression model provide superior forecasts of volatility. However, the various model rankings are shown to be sensitive to the error statistic used to assess the accuracy of the forecasts. Nevertheless, a clear message is that volatility forecasting is a notoriously difficult task.",
author = "Brailsford, {Timothy J.} and Faff, {Robert W.}",
year = "1996",
month = "4",
doi = "10.1016/0378-4266(95)00015-1",
language = "English",
volume = "20",
pages = "419--438",
journal = "Journal of Banking and Finance",
issn = "0378-4266",
publisher = "Elsevier",
number = "3",

}

An evaluation of volatility forecasting techniques. / Brailsford, Timothy J.; Faff, Robert W.

In: Journal of Banking and Finance, Vol. 20, No. 3, 04.1996, p. 419-438.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - An evaluation of volatility forecasting techniques

AU - Brailsford, Timothy J.

AU - Faff, Robert W.

PY - 1996/4

Y1 - 1996/4

N2 - The existing literature contains conflicting evidence regarding the relative quality of stock market volatility forecasts. Evidence can be found supporting the superiority of relatively complex models (including ARCH class models), while there is also evidence supporting the superiority of more simple alternatives. These inconsistencies are of particular concern because of the use of, and reliance on, volatility forecasts in key economic decision-making and analysis, and in asset/option pricing. This paper employs daily Australian data to examine this issue. The results suggest that the ARCH class of models and a simple regression model provide superior forecasts of volatility. However, the various model rankings are shown to be sensitive to the error statistic used to assess the accuracy of the forecasts. Nevertheless, a clear message is that volatility forecasting is a notoriously difficult task.

AB - The existing literature contains conflicting evidence regarding the relative quality of stock market volatility forecasts. Evidence can be found supporting the superiority of relatively complex models (including ARCH class models), while there is also evidence supporting the superiority of more simple alternatives. These inconsistencies are of particular concern because of the use of, and reliance on, volatility forecasts in key economic decision-making and analysis, and in asset/option pricing. This paper employs daily Australian data to examine this issue. The results suggest that the ARCH class of models and a simple regression model provide superior forecasts of volatility. However, the various model rankings are shown to be sensitive to the error statistic used to assess the accuracy of the forecasts. Nevertheless, a clear message is that volatility forecasting is a notoriously difficult task.

UR - http://www.scopus.com/inward/record.url?scp=0030117828&partnerID=8YFLogxK

U2 - 10.1016/0378-4266(95)00015-1

DO - 10.1016/0378-4266(95)00015-1

M3 - Article

VL - 20

SP - 419

EP - 438

JO - Journal of Banking and Finance

JF - Journal of Banking and Finance

SN - 0378-4266

IS - 3

ER -