Modeling Nordic Stock Returns with Asymmetric GARCH models
This paper investigates the presence of asymmetric GARCH effects in a number of equity return series, and compare the modeling performance of seven different conditional variance models, within the parametric GARCH class of models. The data consists of daily returns for 45 Nordic stocks, during the period July 1991 to July 1996. The models investigated are: EGARCH, GJR, TGARCH, A- PARCH, GQARCH, VS-ARCH, and LSTGARCH. In all these models the conditional variance is a function of the sign of lagged residuals. Thus, the models can capture the often reported negative correlation between lagged returns and conditional variance. In the paper I also introduce three new procedures for asymmetry testing. The proposed LM tests, which are based on the results of Wooldridge , allow for heterokurtosis under the null. Asymmetries are detected for only 12 of the 45 series. The specifications GJR, TGARCH, and GQARCH appear to be superior for modeling the dynamics of the conditional variance. Furthermore, I show that the use of robust test statistics is advisable.
|Date of creation:||Mar 1997|
|Date of revision:|
|Contact details of provider:|| Postal: |
Phone: +46-(0)8-736 90 00
Fax: +46-(0)8-31 01 57
Web page: http://www.hhs.se/Email:
More information through EDIRC
When requesting a correction, please mention this item's handle: RePEc:hhs:hastef:0164. See general information about how to correct material in RePEc.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: (Helena Lundin)
If references are entirely missing, you can add them using this form.