July 1st, 2005, 4:17 pm
Hi everyone.I've been doing some modelling in eviews. Especifically a Garch(1,1) model. I've got pretty good results, but I also have a little doubt. The results I got are as follows:Dependent Variable: RIPSA Method: ML - ARCH (Marquardt) Date: 07/01/05 Time: 13:01 Sample(adjusted): 2 626 Included observations: 625 after adjusting endpoints Convergence achieved after 13 iterations Bollerslev-Wooldrige robust standard errors & covariance Variance backcast: ON Coefficient Std. Error z-Statistic Prob. C 0.001233 0.000254 4.852142 0.0000 Variance Equation C 3.10E-06 1.46E-06 2.121323 0.0339ARCH(1) 0.130599 0.035055 3.725553 0.0002GARCH(1) 0.824790 0.047168 17.48616 0.0000 R-squared -0.000095 Mean dependent var 0.001154Adjusted R-squared -0.004927 S.D. dependent var 0.008059S.E. of regression 0.008079 Akaike info criterion -6.880694Sum squared resid 0.040536 Schwarz criterion -6.852293Log likelihood 2154.217 Durbin-Watson stat 1.599351--------------------------------------------------------------------------------------------------------My question is: how can I forecast using the above information? I want to get a especific number and I don't know how to do it. I know how to do it in a simple regression model but not with a Garch model.