Abstract: The objective of this investigation presents Combine White Noise (CWN) Model that outperform the Exponential Generalized Autoregressive Conditional Heteroscedasticity (EGARCH). This study employed the GDP data set of two countries to compare the results of the new CWN Model with existing EGARCH Model. The empirical analysis for the two countries revealed that CWN proved to be more appropriate model. The inference of CWN yielded a reliable outcome of lower information criteria with higher log likelihood values in each country data evaluation while EGARCH revealed higher information criteria and lower log likelihood values when comparing the two models. CWN provided a better forecast output with lower forecast errors values in each country whereas EGARCH offered higher values of forecast errors. CWN estimation was efficient in both countries as the determinant of the residual of covariance matrix is approximately zero while AU has better estimation efficiency than UK. This will assist the policy makers to plan for reliable economy of a society.
Ayodele Abraham Agboluaje, Suzilah Ismail and Chee Yin Yip, 2016. Modelling the Asymmetric Volatility with Combine White Noise Across Australia and United Kingdom GDP Data Set. Research Journal of Applied Sciences, 11: 1427-1431.