Using CAViaR models with implied volatility for value-at-risk estimation

Jooyoung Jeon, James Taylor

Research output: Contribution to journalArticle

16 Citations (Scopus)

Abstract

This paper proposes VaR estimation methods that are a synthesis of conditional autoregressive value at risk (CAViaR) time series models and implied volatility. The appeal of this proposal is that it merges information from the historical time series and the different information supplied by the market’s expectation of risk. Forecast combining methods, with weights estimated using quantile regression, are considered. We also investigate plugging implied volatility into the CAViaR models, a procedure that has not been considered in the VaR area so far. Results for daily index returns indicate that the newly proposed methods are comparable or superior to individual methods, such as the standard CAViaR models and quantiles constructed from implied volatility and the empirical distribution of standardised residual. We find that the implied volatility has more explanatory power as the focus moves further out into the left tail of the conditional distribution of S&P500 daily returns.
LanguageEnglish
Pages62–74
Number of pages13
JournalJournal of Forecasting
Volume32
Issue number1
Early online date27 Oct 2011
DOIs
Publication statusPublished - Jan 2013

Fingerprint

Implied Volatility
Value at Risk
Time series
Quantile Regression
Empirical Distribution
Appeal
Time Series Models
Conditional Distribution
Quantile
Model
Forecast
Standard Model
Tail
Synthesis
Value at risk
Implied volatility

Keywords

  • value at risk
  • CAViaR
  • implied volatility
  • quantile regression
  • combining

Cite this

Jeon, Jooyoung ; Taylor, James. / Using CAViaR models with implied volatility for value-at-risk estimation. In: Journal of Forecasting. 2013 ; Vol. 32, No. 1. pp. 62–74.
@article{6c41422c01324a8a88d048c7657b155d,
title = "Using CAViaR models with implied volatility for value-at-risk estimation",
abstract = "This paper proposes VaR estimation methods that are a synthesis of conditional autoregressive value at risk (CAViaR) time series models and implied volatility. The appeal of this proposal is that it merges information from the historical time series and the different information supplied by the market’s expectation of risk. Forecast combining methods, with weights estimated using quantile regression, are considered. We also investigate plugging implied volatility into the CAViaR models, a procedure that has not been considered in the VaR area so far. Results for daily index returns indicate that the newly proposed methods are comparable or superior to individual methods, such as the standard CAViaR models and quantiles constructed from implied volatility and the empirical distribution of standardised residual. We find that the implied volatility has more explanatory power as the focus moves further out into the left tail of the conditional distribution of S&P500 daily returns.",
keywords = "value at risk, CAViaR, implied volatility, quantile regression, combining",
author = "Jooyoung Jeon and James Taylor",
year = "2013",
month = "1",
doi = "10.1002/for.1251",
language = "English",
volume = "32",
pages = "62–74",
journal = "Journal of Forecasting",
issn = "0277-6693",
number = "1",

}

Using CAViaR models with implied volatility for value-at-risk estimation. / Jeon, Jooyoung; Taylor, James.

In: Journal of Forecasting, Vol. 32, No. 1, 01.2013, p. 62–74.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Using CAViaR models with implied volatility for value-at-risk estimation

AU - Jeon, Jooyoung

AU - Taylor, James

PY - 2013/1

Y1 - 2013/1

N2 - This paper proposes VaR estimation methods that are a synthesis of conditional autoregressive value at risk (CAViaR) time series models and implied volatility. The appeal of this proposal is that it merges information from the historical time series and the different information supplied by the market’s expectation of risk. Forecast combining methods, with weights estimated using quantile regression, are considered. We also investigate plugging implied volatility into the CAViaR models, a procedure that has not been considered in the VaR area so far. Results for daily index returns indicate that the newly proposed methods are comparable or superior to individual methods, such as the standard CAViaR models and quantiles constructed from implied volatility and the empirical distribution of standardised residual. We find that the implied volatility has more explanatory power as the focus moves further out into the left tail of the conditional distribution of S&P500 daily returns.

AB - This paper proposes VaR estimation methods that are a synthesis of conditional autoregressive value at risk (CAViaR) time series models and implied volatility. The appeal of this proposal is that it merges information from the historical time series and the different information supplied by the market’s expectation of risk. Forecast combining methods, with weights estimated using quantile regression, are considered. We also investigate plugging implied volatility into the CAViaR models, a procedure that has not been considered in the VaR area so far. Results for daily index returns indicate that the newly proposed methods are comparable or superior to individual methods, such as the standard CAViaR models and quantiles constructed from implied volatility and the empirical distribution of standardised residual. We find that the implied volatility has more explanatory power as the focus moves further out into the left tail of the conditional distribution of S&P500 daily returns.

KW - value at risk

KW - CAViaR

KW - implied volatility

KW - quantile regression

KW - combining

UR - http://onlinelibrary.wiley.com/doi/10.1002/for.1251/full

U2 - 10.1002/for.1251

DO - 10.1002/for.1251

M3 - Article

VL - 32

SP - 62

EP - 74

JO - Journal of Forecasting

T2 - Journal of Forecasting

JF - Journal of Forecasting

SN - 0277-6693

IS - 1

ER -