A question about correlation analysis

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

kelland
Posts: 2
Joined: Sat Aug 13, 2011 9:07 am

A question about correlation analysis

Postby kelland » Sat Aug 13, 2011 9:24 am

hello! There are two series, X and Y. I want to know if they are correlated. So I use the Covariance Analysis to test them. Now I have a question when I use the correlation analysis. The method is called "Covariance Analysis: Ordinary (uncentered)". The results are very different from the results by using "Covariance Analysis: Ordinary ". So I want to know,
1. What is the "Covariance Analysis: Ordinary (uncentered)" ? How does eviews6 calculate the correlation coefficent and the probability when I using this method?
2. What is the diffence between "Covariance Analysis: Ordinary (uncentered)" and "Covariance Analysis: Ordinary "?

startz
Non-normality and collinearity are NOT problems!
Posts: 3798
Joined: Wed Sep 17, 2008 2:25 pm

Re: A question about correlation analysis

Postby startz » Sat Aug 13, 2011 9:30 am

Have you looked at EViews help file? The formulas are given there. (At least for version 7.)

kelland
Posts: 2
Joined: Sat Aug 13, 2011 9:07 am

Re: A question about correlation analysis

Postby kelland » Sat Aug 13, 2011 10:54 pm

Thanks a lot!


Return to “Estimation”

Who is online

Users browsing this forum: No registered users and 2 guests