Re: Correlation: Sets of Economic Data

From: Richard Ulrich (Rich.Ulrich_at_comcast.net)
Date: 07/18/04 

Date: Sun, 18 Jul 2004 16:48:24 -0400

On Sun, 18 Jul 2004 01:04:13 GMT, "John Gregory"
<jaygreg90@hotmail.com> wrote:

>
> >> The really big problem, which makes simple, naive correlations
> > next to useless, is that the observations are time-series, with
> > large auto-correlations. Google <specious correlation<<
>
> And this tells me nothing. Since you consider the correlation described to

oops! I like the word 'specious' too much, and I didn't test that
one.

Should have been < spurious correlation > which gets 92 thousand
hits across the web, and 131 threads for sci.stat.* alone.

Add terms like FAQ or tutorial, for further reduction of counts.

My point: You don't have to worry much about linearity when
the logical problems are so severe. 

-- 
Rich Ulrich, wpilib@pitt.edu
http://www.pitt.edu/~wpilib/index.html