|Date: ||Wed, 5 Jan 2005 19:59:08 -0800|
|Reply-To: ||BSchwartz <brian@HOMEBOYS.DK>|
|Sender: ||"SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>|
|From: ||BSchwartz <brian@HOMEBOYS.DK>|
|Subject: ||correlation and time series|
|Content-Type: ||text/plain; charset="iso-8859-1"|
I want to assess whether or not there is a significant correlation
between two variables 'spend' and 'score' across time. Sounds easy, or
However, my data is structured as follows:
400.000 customers' 'spend' and 'score' has been observed for 17 time
periods. That gives me 34 variables for each customer:
spend_1 spend_2 ...etc..... and score_1 score_2....etc...
The theory is that there is a positive correlation between spending
behaviour and scoring but I don't know how to prove it.
Can anyone put me on the right track ?
My question is both theoretically and practically (using SAS).