Date: Thu, 28 Apr 2005 15:09:17 -0400
Reply-To: "Kraan, Egon" <ekraan@BeechAcres.org>
Sender: "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From: "Kraan, Egon" <ekraan@BeechAcres.org>
Subject: Re: Factor Analysis -- never done before and need help
Content-Type: text/plain; charset="iso-8859-1"
Since we are recommending sources, I'd like to throw in Chapter 11 in James Stevens' Applied Multivariate Statistics for the Social Sciences.
======================================
Egon Kraan
Beech Acres
Program Evaluation & Quality Improvement
ekraan@BeechAcres.org
http://www.beechacres.org
-----Original Message-----
From: SPSSX(r) Discussion [mailto:SPSSX-L@LISTSERV.UGA.EDU]On Behalf Of
Johnson, Jennifer
Sent: Thursday, April 28, 2005 9:50 AM
To: SPSSX-L@LISTSERV.UGA.EDU
Subject: Factor Analysis -- never done before and need help
I am a somewhat newbie to SPSS -- I've been hacking around it in off and
on for a year, but it's only been in the past 3 months that I've really
gotten into it and learned how to write syntax (still a new language but
coming along).
Anyhow, we conducted a survey, and I have 64 image questions that I
would like to use factor analysis on to boil down to a more managable
number of items. I don't know anything about rotation and all that, and
when I do factor analysis, I see that it gives me 13 factors -- the
first one accounts for the greatest correlation, the others drop down
considerably after that.
Is there a good book on Factor Analysis in SPSS or could anyone give me
some advice in determining what's what? I know that's a giant request,
but I guess I am exceptionally needy on this project.
Many thanks in advance!
Jennifer Johnson
Research Manager
Morris Communications
725 Broad Street
Augusta, GA 30901
706-823-3470
jennifer.johnson@morris.com
-----Original Message-----
From: SPSSX(r) Discussion [mailto:SPSSX-L@LISTSERV.UGA.EDU] On Behalf Of
Bob Schacht
Sent: Wednesday, April 27, 2005 9:36 PM
To: SPSSX-L@LISTSERV.UGA.EDU
Subject: Re: instant statisticians?
At 11:26 AM 4/25/2005, Nels Tomlinson wrote:
>Yes, ``instant statisticians'' may not be the majority of the
>questioners, but they are the majority of the ones that stick in one's
>craw...
I'm a relative newbie to this list, but I've been using SPSSX since the
days when it was only run on mainframes. I've also been a statistical
consultant, and a statistical programmer for a University computer
center (though that was long ago). I've also recently migrated to this
list from an SPSS list on Yahoo Groups, where there seem to be more
questions from left field. Or rather seemingly from 3rd world countries
where analysts seemed to employ statistical procedures chosen at
random-- but perhaps I was not paying sufficiently close attention.
Some of the annoying statistical questions resemble a current
statistical fashion statement. For example, Factor Analysis for a while
was regarded as the greatest thing since sliced bread, and you were
regarded as a beginner until you had published at least one paper using
Factor Analysis. The most common question was not "Does factor analysis
make any sense in this application?" but "How can I do factor analysis
with this data?" More recently, logistic regression seems to be the
method of choice, whether it fits or not. I think there may also be
certain pressures in Grad School that drive the choice of methods. I
generally prefer to use the simplest statistic that will get the job
done.
I am in a new job, in which large multiple data sets must be matched,
duplicate cases identified and removed, and for which it seems that
drop-down menus often don't seem adequate, so I am having to write more
syntax than usual. I have done OK so far, but occasionally may need
advice about writing syntax statements. I use the syntax manual on my
hard drive mostly (It is SO nice to be able to search it
electronically!), but may occasionally get stumped. I'll try to keep any
questions well-focused.
Bob
Robert M. Schacht, Ph.D. <schacht@hawaii.edu>
Pacific Basin Rehabilitation Research & Training Center
1268 Young Street, Suite #204
Research Center, University of Hawaii
Honolulu, HI 96814
