A empirical study of oneday risk prognosis models, using ValueatRisk and three different GARCHmodels
(2013) NEKH01 20121Department of Economics
 Abstract
 This thesis assess three different conditional variance models from the GARCH family  GARCH(1,1), EGARCH(1,1) and GJRGARCH(1,1)  and their accuracy in making oneday forecasts together with Value at Risk. The study is made on the daily returns of the OMX Stockholm 30 index between 20020101 and 2010 1231. A five year insample set was used to estimate the model parameters and to make oneday VaR predictions at 90%, 95% and 99% confidence level the following year (outofsample). This process was run four times where the in and outof sample were updated with one year. A total of four VaR forecasts was produced for each model and for each VaR level. Christoffersen’s three likelihood ratio tests were used to evaluate the models... (More)
 This thesis assess three different conditional variance models from the GARCH family  GARCH(1,1), EGARCH(1,1) and GJRGARCH(1,1)  and their accuracy in making oneday forecasts together with Value at Risk. The study is made on the daily returns of the OMX Stockholm 30 index between 20020101 and 2010 1231. A five year insample set was used to estimate the model parameters and to make oneday VaR predictions at 90%, 95% and 99% confidence level the following year (outofsample). This process was run four times where the in and outof sample were updated with one year. A total of four VaR forecasts was produced for each model and for each VaR level. Christoffersen’s three likelihood ratio tests were used to evaluate the models forecast accuracy. The results points toward GARCH(1,1) being the most accurate model, since the model was not rejected by any of the Christoffersen’s tests and at any VaR levels. However, limitations such as the number of observations used in the outofsample set, the number of model parameters to be estimated for each model and the assumed standard normally distributed innovations and return series may have had en effect on the result. (Less)
Please use this url to cite or link to this publication:
http://lup.lub.lu.se/studentpapers/record/3562561
 author
 Berg, Magnus ^{LU} and Sternbeck Fryxell, Hannes ^{LU}
 supervisor

 Karl Larsson ^{LU}
 organization
 course
 NEKH01 20121
 year
 2013
 type
 M2  Bachelor Degree
 subject
 keywords
 GARCHmodels, Value at Risk, VaR, GARCH, EGARCH, GJRGARCH, forecasting, OMXS30
 language
 English
 id
 3562561
 date added to LUP
 20130402 10:05:32
 date last changed
 20130402 10:05:32
@misc{3562561, abstract = {This thesis assess three different conditional variance models from the GARCH family  GARCH(1,1), EGARCH(1,1) and GJRGARCH(1,1)  and their accuracy in making oneday forecasts together with Value at Risk. The study is made on the daily returns of the OMX Stockholm 30 index between 20020101 and 2010 1231. A five year insample set was used to estimate the model parameters and to make oneday VaR predictions at 90%, 95% and 99% confidence level the following year (outofsample). This process was run four times where the in and outof sample were updated with one year. A total of four VaR forecasts was produced for each model and for each VaR level. Christoffersen’s three likelihood ratio tests were used to evaluate the models forecast accuracy. The results points toward GARCH(1,1) being the most accurate model, since the model was not rejected by any of the Christoffersen’s tests and at any VaR levels. However, limitations such as the number of observations used in the outofsample set, the number of model parameters to be estimated for each model and the assumed standard normally distributed innovations and return series may have had en effect on the result.}, author = {Berg, Magnus and Sternbeck Fryxell, Hannes}, keyword = {GARCHmodels,Value at Risk,VaR,GARCH,EGARCH,GJRGARCH,forecasting,OMXS30}, language = {eng}, note = {Student Paper}, title = {A empirical study of oneday risk prognosis models, using ValueatRisk and three different GARCHmodels}, year = {2013}, }