Modelling and Forecasting Volatility of Stock Index Return Using GARCH Models: an Empirical Evidence of Argentina
Modelling and forecasting stock market volatility has been one of the most important topics in financial econometrics during the last years. In an attempt to contribute to empirical literature, this thesis examines stock return volatility in Argentine stock market and evaluates the forecasting perfo...
| Main Author: | |
|---|---|
| Format: | Dissertation (University of Nottingham only) |
| Language: | English |
| Published: |
2014
|
| Online Access: | https://eprints.nottingham.ac.uk/27379/ |
| _version_ | 1848793359465840640 |
|---|---|
| author | Xenofontos, Andreas |
| author_facet | Xenofontos, Andreas |
| author_sort | Xenofontos, Andreas |
| building | Nottingham Research Data Repository |
| collection | Online Access |
| description | Modelling and forecasting stock market volatility has been one of the most important topics in financial econometrics during the last years. In an attempt to contribute to empirical literature, this thesis examines stock return volatility in Argentine stock market and evaluates the forecasting performance of GARCH-type models in terms of their out-of-sample forecasting accuracy. Both symmetric and asymmetric models are applied, using both daily and weekly frequency data of Merval Index over the twelve year period from January 2002 to August 2014. The models are estimated using three distributions which are Student’s-t Distribution, Generalized Error Distribution and Gaussian Distribution.
The findings suggest that Argentine stock market volatility is time varying, persistent, predictable and asymmetric, with negative shocks having a greater impact on volatility than positive shocks of the same magnitude. The results based on out-of-sample forecasts provide evidence of superiority of models based on non-normal distributions. The asymmetric GJR-GARCH(1,1) outperforms other models in forecasting conditional volatility of daily frequency returns while the fundamental GARCH(1,1) performs most well in forecasting volatility of weekly frequency returns. The findings are evidenced by three different error measurements which evaluate the out-of-sample forecasting accuracy. Furthermore, although this paper checks for a risk-return relationship in the stock market under consideration, there is not any statistical evidence to support the existence of such relationship. These empirical results have important significance in portfolio management and in risk management process. |
| first_indexed | 2025-11-14T18:59:03Z |
| format | Dissertation (University of Nottingham only) |
| id | nottingham-27379 |
| institution | University of Nottingham Malaysia Campus |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-14T18:59:03Z |
| publishDate | 2014 |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | nottingham-273792017-10-19T13:58:11Z https://eprints.nottingham.ac.uk/27379/ Modelling and Forecasting Volatility of Stock Index Return Using GARCH Models: an Empirical Evidence of Argentina Xenofontos, Andreas Modelling and forecasting stock market volatility has been one of the most important topics in financial econometrics during the last years. In an attempt to contribute to empirical literature, this thesis examines stock return volatility in Argentine stock market and evaluates the forecasting performance of GARCH-type models in terms of their out-of-sample forecasting accuracy. Both symmetric and asymmetric models are applied, using both daily and weekly frequency data of Merval Index over the twelve year period from January 2002 to August 2014. The models are estimated using three distributions which are Student’s-t Distribution, Generalized Error Distribution and Gaussian Distribution. The findings suggest that Argentine stock market volatility is time varying, persistent, predictable and asymmetric, with negative shocks having a greater impact on volatility than positive shocks of the same magnitude. The results based on out-of-sample forecasts provide evidence of superiority of models based on non-normal distributions. The asymmetric GJR-GARCH(1,1) outperforms other models in forecasting conditional volatility of daily frequency returns while the fundamental GARCH(1,1) performs most well in forecasting volatility of weekly frequency returns. The findings are evidenced by three different error measurements which evaluate the out-of-sample forecasting accuracy. Furthermore, although this paper checks for a risk-return relationship in the stock market under consideration, there is not any statistical evidence to support the existence of such relationship. These empirical results have important significance in portfolio management and in risk management process. 2014-12 Dissertation (University of Nottingham only) NonPeerReviewed application/pdf en https://eprints.nottingham.ac.uk/27379/1/Modelling_and_Forecasting_Volatility_Argentina_Stock_Index.pdf Xenofontos, Andreas (2014) Modelling and Forecasting Volatility of Stock Index Return Using GARCH Models: an Empirical Evidence of Argentina. [Dissertation (University of Nottingham only)] (Unpublished) |
| spellingShingle | Xenofontos, Andreas Modelling and Forecasting Volatility of Stock Index Return Using GARCH Models: an Empirical Evidence of Argentina |
| title | Modelling and Forecasting Volatility of Stock Index Return Using GARCH Models: an Empirical Evidence of Argentina |
| title_full | Modelling and Forecasting Volatility of Stock Index Return Using GARCH Models: an Empirical Evidence of Argentina |
| title_fullStr | Modelling and Forecasting Volatility of Stock Index Return Using GARCH Models: an Empirical Evidence of Argentina |
| title_full_unstemmed | Modelling and Forecasting Volatility of Stock Index Return Using GARCH Models: an Empirical Evidence of Argentina |
| title_short | Modelling and Forecasting Volatility of Stock Index Return Using GARCH Models: an Empirical Evidence of Argentina |
| title_sort | modelling and forecasting volatility of stock index return using garch models: an empirical evidence of argentina |
| url | https://eprints.nottingham.ac.uk/27379/ |