Page 1 of 1

about estimate equation and BDS test

Posted: Tue Sep 23, 2008 8:45 am
by tg128
Just wondering if there is anyway I can estimate more than one equation in the estimate equation window please??

another question, when use BDS test, there are both BDS statistic and z-statistic, on what ground I should reject the null hypothesis of the BDS test?? what is v-statistic??

Posted: Tue Sep 23, 2008 8:48 am
by EViews Gareth
You cannot estimate more than one equation in an equation object. You'll have to use a System.

Posted: Tue Sep 23, 2008 8:56 am
by tg128
You cannot estimate more than one equation in an equation object. You'll have to use a System.
right, what if I want to compute information criteria to select ARMA model, how can I use system to do that please?

Posted: Tue Sep 23, 2008 9:05 am
by EViews Gareth
You'll have to compute the ICs yourself, using the determinant residual covariance to compute the likelihood.

Re: about estimate equation and BDS test

Posted: Thu Sep 25, 2008 5:46 pm
by EViews Chris
another question, when use BDS test, there are both BDS statistic and z-statistic, on what ground I should reject the null hypothesis of the BDS test?? what is v-statistic??
The z-statistic is the BDS-statistic divided by the standard error. It is the final result that is used for the hypothesis test (because it is asymptotically standard normal).

EViews reports the probability that the given z-statistic would be observed from iid data in the Prob. column of the output, so you would reject the hypothesis that the series is iid if the reported probability is small.

The V-statistics are intermediate results used in calculating some of the other numbers. You can ignore them if you're only interested in the final results.