Analysis of Nigerian Stock Market Returns Volatility Using Skewed ARMA-GARCH Model
No Thumbnail Available
Date
2013
Authors
Adewole, A. P.
Isenah, M.G
Agwuegbo, S.O
Journal Title
Journal ISSN
Volume Title
Publisher
Journal of Nigerian Statistical Association
Abstract
This study used ARMA-GARCH type volatility models for predicting future values of the Nigerian stock market's percentage nominal returns and volatility. The data used in the study are time series data of the monthly Nigerian Stock Exchange All-Share-Index for the period of January 1990 to December 2012. The data was further segmented into in-sample and out-sample data sets for model building and out-of-sample forecast comparisons. Three ARMA(1,2)-GARCH(1, 1) models with skewed normal distribution (SNORM), skewed Student-t distribution (SSTD) and skewed generalized error distribution (SGED) were fitted. In-sample model selections were based on the Akaike Information Criterion (AIC), Bayes Information Criterion ( BIC), Schwarz Information Criterion ( SIC) and the Hannan - Quinn Information Criterion ( HQIC), while out-sample forecast evaluations were based on the Forecast Root Mean Square Error (FRMSE) and Forecast Mean Absolute Error (FMAE) metrics. The results of the study revealed the asymmetry) inherent in the stock market returns distribution with kurtosis that exceeds that of normal distribution. The ARMA (1,2)-GARCH (1,1) model with skewed normal error distribution slightly outperformed the other models in the out-sample forecast evaluations, but for short-run forecasts the three models are quite adequate.
Description
Staff publication
Keywords
GARCH model , Skewed distribution , Conditional mean , Conditional variance , Nigerian stock market , Research Subject Categories::TECHNOLOGY::Information technology
Citation
Isenah, M.G., Agwuegbo, S.O and Adewole, A.P (2013). Analysis of Nigerian Stock Market Returns Volatility Using Skewed ARMA-GARCH models. Journal of Nigerian Statistical Association, Vol 25, 31-50pp.