Modeling the heteroscedasticity in data distribution
The main objective of this study is to provide a model that will uplift the weaknesses of the existing model for efficient estimation. Generalized autoregressive conditional heteroscedasticity (GARCH) family models weaknesses were overcome by the new Combine White Noise (CWN) model which proved to...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Research India Publications
2016
|
| Subjects: | |
| Online Access: | http://repo.uum.edu.my/21520/1/GJPAM%2012%201%202016%20313%20322.pdf http://repo.uum.edu.my/21520/ http://www.ripublication.com/gjpam16/gjpamv12n1_27.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Universiti Utara Malaysia |
| Language: | English |
| Summary: | The main objective of this study is to provide a model that will uplift the weaknesses of the existing model for efficient estimation. Generalized autoregressive conditional heteroscedasticity (GARCH) family models
weaknesses were overcome by the new Combine White Noise (CWN) model which proved to be more efficient.CWN estimation passed stability condition, stationary, serial correlation, the ARCH effect tests and it also passed the
Levene’s test of equal variances using both Australia (A.U.) and United States (U.S.) GDP data sets. The CWN estimation produced better results with minimum information criteria and high log likelihood values in both U.S. and A.U. data estimation.CWN has the minimum forecast errors which were better results when compare with the GARCH model dynamic evaluation forecast errors in both countries.The determinant of the residual of covariance matrix values revealed that CWN was efficient in the two countries, but A.U.was more efficient.Based on every result in the empirical analysis of the two countries, CWN was the more appropriate model. |
|---|