|Date: ||Tue, 25 Apr 2006 17:01:59 -0700|
|Reply-To: ||Michael Breen <email@example.com>|
|Sender: ||"SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>|
|From: ||Michael Breen <firstname.lastname@example.org>|
|Subject: ||Factor Analysis question|
|Content-Type: ||text/html; format=flowed|
<html><div style='background-color:'><DIV class=RTE>I was wondering if could ask some advice on analyzing the results of a factor analysis I performed. I am looking at a bunch of questions from a standard survey I run at my company. There seem to be one or two questions that could fall on to one or two factors. If I supress coefficients < .4 these two questions wouldn't load on any factors. I decreased it to surpress only coefficients < .3 and these two now show up on a number of different factors.
<DIV><BR>Taking one question for instance, it is originally grouped in with a bunch of other questions that seem to logically fit together. But its coeffiecient on this group is .365 and it loads on another factor at .370. My question is, is this close enough to where I can make a choice to keep it loaded on to its orginally grouped set of questions? Or since the coefficient is higher on the other factor that it needs to be grouped with that factor. I hope this makes sense.</DIV>