Comparison of forecasting performance between MODWT-GARCH(1,1) and MODWT-EGARCH(1,1) models: Evidence from African stock markets

Many researchers documented that if stock markets' returns series are significantly skewed, linear-GARCH(1,1) grossly underestimates the forecast values of the returns. However, this study showed that the linear Maximal Overlap Discreet Wavelet Transform MODWT-GARCH(1,1) actually gives an acc...

詳細記述

保存先:
書誌詳細
主要な著者: Ismail, Mohd Tahir, Audu, Buba, Tumala, Mohammed Musa
フォーマット: 論文
言語:English
出版事項: Elsevier 2016
主題:
オンライン・アクセス:http://eprints.usm.my/38472/1/Comparison_of_forecasting_performance_between_MODWT-GARCH%281%2C1%29_and_MODWT-EGARCH%281%2C1%29.pdf
http://eprints.usm.my/38472/
http://www.keaipublishing.com/en/journals/jfds/
タグ: タグ追加
タグなし, このレコードへの初めてのタグを付けませんか!
その他の書誌記述
要約:Many researchers documented that if stock markets' returns series are significantly skewed, linear-GARCH(1,1) grossly underestimates the forecast values of the returns. However, this study showed that the linear Maximal Overlap Discreet Wavelet Transform MODWT-GARCH(1,1) actually gives an accurate forecast value of the returns. The study used the daily returns of four African countries' stock market indices for the period January 2, 2000, to December 31, 2014. The Maximal Overlap Discreet Wavelet Transform-GARCH(1,1) model and the Maximal Overlap Discreet Wavelet Transform-EGARCH(1,1) model are exhaustively compared. The results show that although both models fit the returns data well, the forecast produced by the Maximal Overlap Discreet Wavelet Transform-EGARCH(1,1) model actually underestimates the observed returns whereas the Maximal Overlap Discreet Wavelet Transform-GARCH(1,1) model generates an accurate forecast value of the observed returns.