Multiple Variance Ratio Test

For technical questions regarding estimation of single equations, systems, VARs, Factor analysis and State Space Models in EViews. General econometric questions and advice should go in the Econometric Discussions forum.

Moderators: EViews Gareth, EViews Moderator

ssk322
Posts: 13
Joined: Fri Jan 17, 2014 4:36 am

Multiple Variance Ratio Test

Postby ssk322 » Thu Feb 12, 2015 1:50 pm

Hi All,

I have read the manual over and over again in terms of trying to apply the multiple variance ratio test as suggested by Lo and Mackinlay as well as Chow and Denning, but I am struggling to implement on multiple series and not just the singular series. I am using Eviews 8.

Please can you kindly advise.

Kind regards.

EViews Glenn
EViews Developer
Posts: 2682
Joined: Wed Oct 15, 2008 9:17 am

Re: Multiple Variance Ratio Test

Postby EViews Glenn » Thu Feb 12, 2015 2:20 pm

I'm confused. What is it that you want to do? I believe that those tests are all for a single series but testing at different lags.

ssk322
Posts: 13
Joined: Fri Jan 17, 2014 4:36 am

Re: Multiple Variance Ratio Test

Postby ssk322 » Thu Feb 12, 2015 4:07 pm

What I was hoping to do was to apply the variance ratio test towards many variables at one moment rather than singular variables. From what I have read in the literature, it is possible to apply the test within that context. The issue is applying it to eviews.

Appreciate the response.

EViews Glenn
EViews Developer
Posts: 2682
Joined: Wed Oct 15, 2008 9:17 am

Re: Multiple Variance Ratio Test

Postby EViews Glenn » Thu Feb 12, 2015 6:58 pm

I'm still a bit confused by what you wish to do. The VR test is for the properties of a single stochastic process. The multiple tests to which Chow and Denning refer are multiple comparisons on the single series at different sampling intervals. How to perform the latter test is described in the documentation.

If what you want to do is jointly test multiple variables with multiple comparisons, then you'll have to do the tests for the variables separately. If you are willing to make independence assumptions, then you can combine the results.

ssk322
Posts: 13
Joined: Fri Jan 17, 2014 4:36 am

Re: Multiple Variance Ratio Test

Postby ssk322 » Fri Feb 13, 2015 5:43 am

Thanks for the advice, that's what I'm after.

Kind regards.


Return to “Estimation”

Who is online

Users browsing this forum: No registered users and 2 guests