Factor Analysis Question

[Jeff-125]

Factor Analysis is not my strongest area. I have a number of
variables that presumably represent the same latent factor, or at the
most two factors. I could deal with everything if all of the measured
variables were interval measures, but I have some intervals and some
dichotomies.

How might I go about doing some type of factor analysis on data of
these types, and how might I go about creating a set of factor
scores? Can spss do this type of thing, or would I need something like M-Plus?

Thanks

Jeff

[Hector Maletta]

         Dichotomous variables can be regartded as interval variables, and
thus be included in classical factor analysis with SPSS FACTOR command. You
can also use CATCPA, the SPSS categorical factor analysis (which can be used
for categorical or continuous variables), available in the CATEGORIES
module. Both produce factor scores as a by product with the SAVE subcommand.

         Hector

         -----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
Jeff
Sent: 11 July 2007 00:56
To: [hidden email]
Subject: Factor Analysis Question

         Factor Analysis is not my strongest area. I have a number of
         variables that presumably represent the same latent factor, or at
the
         most two factors. I could deal with everything if all of the
measured
         variables were interval measures, but I have some intervals and
some
         dichotomies.

         How might I go about doing some type of factor analysis on data of
         these types, and how might I go about creating a set of factor
         scores? Can spss do this type of thing, or would I need something
like M-Plus?

         Thanks

         Jeff B

[Jeff-125]

At 11:24 PM 7/10/2007, you wrote:
>Dichotomous variables can be regartded as interval variables, and
>thus be included in classical factor analysis with SPSS FACTOR command. You
>can also use CATCPA, the SPSS categorical factor analysis (which can be used
>for categorical or continuous variables), available in the CATEGORIES
>module. Both produce factor scores as a by product with the SAVE subcommand.
>
>          Hector


So what then is the difference between CATCPA and the regular factor analysis?

Thanks

Jeff

[Kooij, A.J. van der]

With only interval and dichotomous variables there is no difference between the results of CATPCA and standard PCA. But CATPCA offers more output options: fit measure (VAF) per variable, biplots, plot of cases labeled with analysis or background variables. And with CATPCA background variables can be included to examine its relationship with the component structure for the analysis variables.
 
Anita van der Kooij
Data Theory Group
Leiden University

________________________________

From: SPSSX(r) Discussion on behalf of Jeff
Sent: Wed 11/07/2007 10:13
To: [hidden email]
Subject: Re: Factor Analysis Question



At 11:24 PM 7/10/2007, you wrote:
>Dichotomous variables can be regartded as interval variables, and
>thus be included in classical factor analysis with SPSS FACTOR command. You
>can also use CATCPA, the SPSS categorical factor analysis (which can be used
>for categorical or continuous variables), available in the CATEGORIES
>module. Both produce factor scores as a by product with the SAVE subcommand.
>
>          Hector


So what then is the difference between CATCPA and the regular factor analysis?

Thanks

Jeff



**********************************************************************
This email and any files transmitted with it are confidential and
intended solely for the use of the individual or entity to whom they
are addressed. If you have received this email in error please notify
the system manager.
**********************************************************************

[Hector Maletta]

         Jeff,
         In addition to Anita's response: CATCPA also deals with categorical
(nominal or ordinal) variables. In that case it not only produces the usual
factor analysis results but also assigns quantitative values to each
category.

         Hector


         -----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
Kooij, A.J. van der
Sent: 11 July 2007 09:46
To: [hidden email]
Subject: Re: Factor Analysis Question

         With only interval and dichotomous variables there is no difference
between the results of CATPCA and standard PCA. But CATPCA offers more
output options: fit measure (VAF) per variable, biplots, plot of cases
labeled with analysis or background variables. And with CATPCA background
variables can be included to examine its relationship with the component
structure for the analysis variables.

         Anita van der Kooij
         Data Theory Group
         Leiden University

         ________________________________

         From: SPSSX(r) Discussion on behalf of Jeff
         Sent: Wed 11/07/2007 10:13
         To: [hidden email]
         Subject: Re: Factor Analysis Question



         At 11:24 PM 7/10/2007, you wrote:
         >Dichotomous variables can be regartded as interval variables, and
         >thus be included in classical factor analysis with SPSS FACTOR
command. You
         >can also use CATCPA, the SPSS categorical factor analysis (which
can be used
         >for categorical or continuous variables), available in the
CATEGORIES
         >module. Both produce factor scores as a by product with the SAVE
subcommand.
         >
         >          Hector


         So what then is the difference between CATCPA and the regular
factor analysis?

         Thanks

         Jeff




**********************************************************************
         This email and any files transmitted with it are confidential and
         intended solely for the use of the individual or entity to whom
they
         are addressed. If you have received this email in error please
notify
         the system manager.

**********************************************************************