This is troublesome for regression. It is likely that the results may
not be good if you have such a low correlation value. In my days as
statistical modeler I would keep a variable if the correlation was .6 or
better.
It seems that anova could be a better approach, but I do not have the
data at hand as you do.
Presumably the learning methods should have some kind of level to see if
they make a difference in the score.
-----Original Message-----
From: SPSSX(r) Discussion [mailto:
[hidden email]] On Behalf Of
Alan Elliott
Sent: Wednesday, February 21, 2007 2:54 PM
To:
[hidden email]
Subject: Ahmed,
Ahmed,
After looking at the data it appears each of the four learing types is
not four categories as I'd assumed, but 4 variables - which look like
they might be considered scale varaibles - it looks like the approach
might be a multiple (linear) regression analysis... I did one quickly
and see that the keeping facts type learning is marginally correlated
with the dependent variable p=.051, when taking the others into
account). I think this might be your approach - you might also examine
interaction effects to see if it might strengthen your model.
Alan C. Elliott
Statistical Analysis Quick Reference Guidebook (Sage)
NOTICE: This e-mail (and any attachments) may contain PRIVILEGED OR
CONFIDENTIAL information and is intended only for the use of the
specific individual(s) to whom it is addressed. It may contain
information that is privileged and confidential under state and federal
law. This information may be used or disclosed only in accordance with
law, and you may be subject to penalties under law for improper use or
further disclosure of the information in this e-mail and its
attachments. If you have received this e-mail in error, please
immediately notify the person named above by reply e-mail, and then
delete the original e-mail. Thank you.
Locked
Feb 21, 2007; 9:54pm
