Comparative Study of Estimation of the Asymmetric in Conditional Variance Using EGARCH Models and CWN Model | Chapter 10 | Mathematics and Computer Science: Contemporary Developments Vol. 7

The aim of the study is to compare the asymmetry in the conditional variance of Exponential Generalized Autoregression Conditional Heteroscdastiicity (EGARCH) with the Combine White Noise (CWN) model to acquire reliable results. The EGARCH has high information criteria and low log likelihood while CWN has minimum information criteria and high log likelihood which makes CWN a more suitable estimation. CWN estimation is more efficient than EGARCH estimation when employing the determinant covariance matrix values. Minimum forecast error in CWN revealed better forecast accuracy when compared with EGARCH. Therefore, CWN estimation results have revealed more efficiency than the EGARCH model estimation in the overall results.

 

Author (s) Details

 

Ayodele Abraham Agboluaje
Department of Mathematical Sciences, Faculty of Natural Sciences, Ibrahim Badamasi Babangida University, Lapai, Nigeria and School of Quantitative Sciences, College of Arts and Sciences, Universiti Utara Malaysia, Malaysia.

 

Suzilah Bt Ismail
School of Quantitative Sciences, College of Arts and Sciences, Universiti Utara Malaysia, Malaysia.

 

Chee Yin Yip
Department of Economics, Faculty of Business and Finance, Universiti Tuanku Abdul Rahman, Malaysia.

 

Please see the book here:- https://doi.org/10.9734/bpi/mcscd/v7/2431

Modeling the Error Term by Moving Average and Generalized Autoregressive Conditional Heteroscedasticity Processes: An Advanced Research | Chapter 10 | Innovations in Science and Technology Vol. 4

 The Combine White Noise model beats the existing Generalized Autoregressive Conditional Heteroscedasticity (GARCH) and Moving Average (MA) models in simulating conditional heteroscedasticity and leverage effect errors, according to this study. The MA process is unable to model data that exposes conditional heteroscedasticity, and the GARCH model is likewise unable to describe the leverage effect. The standardised residuals of GARCH errors are decomposed into a series of white noises, which are then modelled using the Combine White Noise model (CWN). With minimum information criteria and high log likelihood values, CWN model estimate produces the best results. When compared to the MA model, the EGARCH model estimate produces better results in terms of minimum information criterion and high log likelihood values. When compared to the GARCH and MA models dynamic evaluation forecast errors, CWN has the smallest forecast errors, indicating the best results. CWN's findings consistently outperform those of GARCH and MA. The CWN provides good results that enhance the flaws of previous models, which is a contribution of this study to the scientific community.

Author(S) Details

Ayodele Abraham Agboluaje
Department of Mathematical Sciences, Faculty of Natural Sciences, Ibrahim Badamasi Babangida University, Lapai, Nigeria.

Suzilah bt Ismail
School of Quantitative Sciences, College of Arts and Sciences, Universiti Utara Malaysia, Malaysia.

Chee Yin Yip
Department of Economics, Faculty of Business and Finance, Universiti Tuanku Abdul Rahman, Malaysia.

View Book:- https://stm.bookpi.org/IST-V4/article/view/5563