Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Exchange Rate Risk Measurement: Using GARCH Models and Different Residual Distributions for Value-at-risk Forecasts of the Swedish-Krona-to-U.S. Dollar Exchange Rate Volatility
Jönköping University, Jönköping International Business School, JIBS, Business Administration.
2015 (English)Independent thesis Advanced level (degree of Master (One Year)), 10 credits / 15 HE creditsStudent thesis
Abstract [en]

Background: The subprime mortgage crises, and the subsequent world financialcrisis, have provided evidence of the magnitude of the world financialmarkets’ inherent volatility. In the foreign exchange market, the mostactive financial market in the world, risk management and avoidanceare of particular concern. Controlling foreign exchange rate risk hastherefore become one of the top priorities for investors andpolicymakers alike.Purpose: This thesis aims at contributing to an effective risk management inthe foreign exchange market by conducting an empirical analysisdevoted to the measurement of currency risks. Risk measurementoccurs by means of generalized autoregressive conditionallyheteroscedastic (GARCH) models involving different residualdistributions for value-at-risk (VaR) forecasts. The empiricalapplication is the measurement of the Swedish-Krona-to-U.S. Dollarexchange rate risk over the last two decades. The ultimate purpose isto find out which type of VaR forecast is closest to the real loss ofexchange rate returns and, hence, which GARCH model performsbest in measuring the Swedish-Krona-to-U.S. Dollar exchange raterisk. In doing so, the thesis intends to provide policy advice toSwedish investors aiming at making rational decisions in the foreignexchange market in the future through.Method: To fulfill the research purpose, this thesis applies advancedtime-series econometric techniques in the form of GARCH models,used to estimate and forecast the VaR in the Swedish-Krona-to-U.S.Dollar exchange rate. One novelty of the GARCH-VaR approachfound in this thesis is that it is based not on the commonly foundnormal probability distribution but on the generalized errordistribution (GED) as well as the Student’s t-distribution. The lattertwo distributions better capture the peculiar characteristics offinancial time series, such as exchange rate returns, namely, the factthat they are highly peaked and fat-tailed relative to the normaldistribution. Hence, building the analysis on these distributionsshould increase the reliability of the exchange rate risk estimationsand predictions. A second novelty of the GARCH-VaR methodapplied is that it uses comparative modeling analysis to identify thedistribution that helps to predict the Swedish-Krona-to-U.S. Dollarexchange rate risk in the most accurate way.Conclusion: Based on the parametric VaR models, the paper draws appropriateconclusions by comparing the actual exchange rate returns data withthe out of sample VaR values predicted by model of GARCH underdifferent residual distributions and then conduct back testing of VaR.Analysis results show that, at the confidence level of 95%, thepredicted failure rate under residual distribution of normaldistribution compared to values under other residual distributions isthe highest, which proved that the risk of the fluctuation of exchangemay be underestimated by the VaR of normal distribution; At theconfidence level of 99%, three kinds of predicted failure rate of VaRunder different error distribution are very close. Overall, by contrast,the VaR prediction of GARCH model under the residual distributionof t distribution is relatively stable both in confidence level of 95%and 99%, and it is especially suitable for the simulation of fat taildistribution in lower confidence level.

Place, publisher, year, edition, pages
2015.
Keyword [en]
GARCH-t GARCH-GED, value-at-risk, exchange rate volatility, risk measurement
National Category
Business Administration
Identifiers
URN: urn:nbn:se:hj:diva-27231ISRN: JU-IHH-FÖA-2-20150120OAI: oai:DiVA.org:hj-27231DiVA: diva2:821926
Subject / course
IHH, Business Administration
Supervisors
Examiners
Available from: 2015-06-30 Created: 2015-06-16 Last updated: 2015-06-30Bibliographically approved

Open Access in DiVA

No full text

By organisation
JIBS, Business Administration
Business Administration

Search outside of DiVA

GoogleGoogle Scholar

Total: 233 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf