Estimation of Value-at-Risk by extreme value and conventional methods: a comparative evaluation of their predictive performance

Bekiros, Stelios; Georgoutsos, Dimitris A.

doi:10.1016/j.intfin.2004.05.002

Cited by 53 publications

(31 citation statements)

References 14 publications

(20 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…at the 99.5% level, in which it is overcome by the EVT-based method. These results are consistent with previous studies in the sense that EVT is particularly accurate as tails become more extreme (Danielsson and de Vries, 1997;Longin (2000); Assaf (2009);Bekiros and Georgoutsos, 2005). …”

Section: 1supporting

confidence: 93%

“…This theory has been increasingly playing a role in many research areas such as hydrology and climatology where extreme events are not infrequent and can involve important negative (or positive) consequences and, more recently, there has been a number of extreme value studies in the finance literature. Some examples include Embrechts et al (1999), who present a broad basis for understanding the extreme value theory with applications to finance and insurance; Liow (2008), who compares the extreme behaviour of securitized real state and equity market indices representing Asian, European and North American markets; Danielsson and de Vries (1997), who test the predictive performance of various VaR 2 methods for simulated portfolios of seven US stocks concluding that EVT is particularly accurate as tails become more extreme whereas the conventional variance-covariance and the historical simulation methods under-and over-predict losses, respectively; similar results are found in Longin (2000) 3 , Assaf (2009) 4 and Bekiros and Georgoutsos (2005) 5 ; Danielsson and Morimoto (2000) apply EVT to Japanese financial data to confirm the accuracy and stability of this methodology over the GARCH-type techniques; Byström (2004) focuses on the negative distribution tails of the Swedish AFF and the U.S. DOW indices to compare EVT with generalized ARCH approaches and finds EVT to be a generally superior approach both for standard and more extreme VaR quantiles. Nevertheless,…”

Section: Introductionmentioning

confidence: 78%

“…In some papers, the focus is on the marginal or unconditional distribution of the process, without accounting for the conditional heteroscedasticity of most financial data (Christoffersen and Diebold, 2000;Danielsson and de Vries, 2000;Longin, 2000;Bekiros and Georgoutsos, 2005;Gilli and Këllezi, 2006;Assaf, 2009). In this paper, however, we follow McNeil and Frey (2000) to overcome this shortcoming and proceed 2 Value at Risk (VaR) is a generalized measure of market risk which tells you the maximum loss, with a given probability, over a certain time horizon.…”

Section: Fernández (2005) Uses a Sample Comprised Of Several Financiamentioning

confidence: 99%

See 2 more Smart Citations

Extreme value theory versus traditional GARCH approaches applied to financial data: a comparative evaluation

Furió

Diranzo

2013

Quantitative Finance

View full text Add to dashboard Cite

Although stock prices fluctuate, the variations are relatively small and are frequently assumed to be normal distributed on a large time scale. But sometimes these fluctuations can become determinant, especially when unforeseen large drops in asset prices are observed that could result in huge losses or even in market crashes. The evidence shows that these events happen far more often than would be expected under the generalized assumption of normal distributed financial returns. Thus it is crucial to properly model the distribution tails so as to be able to predict the frequency and magnitude of extreme stock price returns. In this paper we follow the approach suggested by McNeil and Frey (2000) and combine the GARCH-type models with the Extreme Value Theory (EVT) to estimate the tails of three financial index returns DJI, FTSE 100 and NIKKEI 225 representing three important financial areas in the world.Our results indicate that EVT-based conditional quantile estimates are much more accurate than those from conventional AR-GARCH models assuming normal or Student's t-distribution innovations when doing out-of-sample estimation (within the insample estimation, this is so for the right tail of the distribution of returns).

show abstract

Section: 1supporting

confidence: 93%

Section: Introductionmentioning

confidence: 78%

Section: Fernández (2005) Uses a Sample Comprised Of Several Financiamentioning

confidence: 99%

See 1 more Smart Citation

Extreme value theory versus traditional GARCH approaches applied to financial data: a comparative evaluation

Furió

Diranzo

2013

Quantitative Finance

View full text Add to dashboard Cite

show abstract

“…Likewise, Bekiros and Georgoutsos (2005) conducted a broad and interesting research, with a comparative evaluation of the predictive performance of various models for Value-at-Risk (VaR). Notably, two methodlogies relating to EVT deserved distinction, the Peaks Over Threshold (POT) and Blocks Maxima (BM).…”

Section: Studies Conductedmentioning

confidence: 99%

Value-at-risk in times of crisis: An analysis in the Brazilian market

Gaio¹,

Pimenta²,

Lima³

et al. 2015

Afr. J. Bus. Manage.

View full text Add to dashboard Cite

show abstract

“…Danielsson et al (1998) and Coronel-Brinzio and Hernandez-Montoya (2004) introduce interesting approaches to this subject. Christoffersen (2003) presents a "rule of thumb" and Neftci (2000) followed by Bekiros and Georgoutsos (2005) estimates u = 1.176 n , where n is the sample standard deviation and 1.176…”

Section: Extreme Value Theory (Evt)mentioning

confidence: 99%