Date:         Wed, 26 Apr 2006 15:23:55 +0200
Reply-To:     a.smulders@beke.nl
Sender:       "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From:         Antoon Smulders <a.smulders@beke.nl>
Subject:      Re: Factor Analysis using different Likert Scales
Comments: To: Spousta Jan <JSpousta@CSAS.CZ>
In-Reply-To:  <FABE7BF4C8A9B647A083DCEB99A792CF185D68@beke01.beke.local>
Content-Type: text/plain; charset="US-ASCII"

Hello Jan

Do I have to take your remark that the results are *not too much* influenced
litteraly? If so, is there some kind of limit? Can I, for instance combine
1-4 scales with 1-10 scales ("scool notes" in some countries)?

Regards,
Antoon Smulders

-----Oorspronkelijk bericht-----
Van: SPSSX(r) Discussion [mailto:SPSSX-L@LISTSERV.UGA.EDU] Namens Spousta
Jan
Verzonden: woensdag 26 april 2006 11:10
Aan: SPSSX-L@LISTSERV.UGA.EDU
Onderwerp: Re: Factor Analysis using different Likert Scales

Hi Mike,

In my opinion it is OK to use 1-4 scales, especially if the solution
gives more sense. In FA, you analyse the correlations and not spreads of
the individual scales, and therefore the results are not too much
influenced by it.

Another possibility would be to fix the number of factor as 6. You have
the right to do it - the default Kaiser rule is only a rule of thumb.

Greetings

Jan

________________________________

From: SPSSX(r) Discussion [mailto:SPSSX-L@LISTSERV.UGA.EDU] On Behalf Of
Michael Breen
Sent: Tuesday, April 25, 2006 10:33 PM
To: SPSSX-L@LISTSERV.UGA.EDU
Subject: Factor Analysis using different Likert Scales


I am trying to analyze some survey data by using factor analysis to
determine which groups of questions could be combined. Almost all of the
questions are on a 1-5 Likert scale. Two of the questions are on a 1-4
scale. When I include these two using the 1-4 scale the way the
variables load on to each of the factors makes sense. But when I exclude
the two on the 1-4 scale I get 8 factors instead of 6. The additional
factors make sense somewhat but they are not as clear.

My question is can you perform a reliable factor analysis with questions
using slightly different likert scales? About 20 of the questions are on
a 1-5 scale and the other two are on a 1-4 scale.

Thanks,

Mike