Help with Categorical Principal Components Analysis

[Katina Dimoulias]

Hi all,

Firstly, thank you to Hector and Kylie for your responses to my previous
question about CATPCA .

Now I desperately need help to a use it........
I have attempted to run CATPCA on my ordinal data (I have previously run
normal factor analysis with principal components), however I am getting a
long list of warnings -  I have no knowledge or understanding about what I
am doing, the correct choices to make in the procedure and how to interpret
the output.  Can anyone help me by pointing me to some literature which
will give me this information, or similar information for CATPCA to that
which is in many SPSS texts explaining each step for Factor analysis, how
to interpret outputs etc.

Thanks,

Katina

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD

[Kooij, A.J. van der]

Hi Katina,
 
The Categories manual gives the information you are looking for; possibly (depending on which SPSS version you have)
it is as a pdf file in you SPSS directory. If not, search the web, it can be downloaded from several sites.
An additional source of information is me (the Leiden Data Theory Group developed the Cateogries procedures). For any questions about using and interpretation you can mail me. Send me the warnings you get.
 
Kind regards,
Anita van der Kooij
Data Theory Group
Leiden University

________________________________

From: SPSSX(r) Discussion on behalf of Katina Dimoulias
Sent: Fri 16/11/2007 00:25
To: [hidden email]
Subject: Help with Categorical Principal Components Analysis



Hi all,

Firstly, thank you to Hector and Kylie for your responses to my previous
question about CATPCA .

Now I desperately need help to a use it........
I have attempted to run CATPCA on my ordinal data (I have previously run
normal factor analysis with principal components), however I am getting a
long list of warnings -  I have no knowledge or understanding about what I
am doing, the correct choices to make in the procedure and how to interpret
the output.  Can anyone help me by pointing me to some literature which
will give me this information, or similar information for CATPCA to that
which is in many SPSS texts explaining each step for Factor analysis, how
to interpret outputs etc.

Thanks,

Katina

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD



**********************************************************************
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.
**********************************************************************

====================To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD

[Kooij, A.J. van der]

In my reply below yesterday I forgot to mention tow more sources of information about CATPCA and about CATREG. Two members of the Data Theory Group recently finished their thesis. Parts of the theses are available at:

https://openaccess.leidenuniv.nl/handle/1887/12386 <https://openaccess.leidenuniv.nl/handle/1887/12386>

Linting, M. Nonparametric inference in nonlinear principal components analysis : exploration and beyond.

The first chapter provides a didactic and practical guide to nonlinear PCA (CATPCA), showing its similarities and differerences to linear PCA, and giving an extensive display of an application to empirical data.

The second chapter is a didactic guide to nonlinear PCA, offering an extensive description of the method including its advantages and disadvantages, followed by an application in which the analytic steps in conducting a nonlinear PCA are described in detail.

 

https://openaccess.leidenuniv.nl/handle/1887/12096 <https://openaccess.leidenuniv.nl/handle/1887/12096>

Van der Kooij, A.J. Prediction accuracy and stability of regression with optimal scaling transformations.

The first chapter provides an non-technical introduction to regression with optimal scaling transformations (CATREG) and describes and illustrates the optimal scaling process graphically (no formula's, only plots).

 

Anita van der Kooij
Data Theory Group
Leiden University

________________________________

From: Kooij, A.J. van der
Sent: Fri 16/11/2007 00:48
To: [hidden email]
Subject: RE: Help with Categorical Principal Components Analysis



Hi Katina,
 
The Categories manual gives the information you are looking for; possibly (depending on which SPSS version you have)
it is as a pdf file in you SPSS directory. If not, search the web, it can be downloaded from several sites.
An additional source of information is me (the Leiden Data Theory Group developed the Cateogries procedures). For any questions about using and interpretation you can mail me. Send me the warnings you get.
 
Kind regards,
Anita van der Kooij
Data Theory Group
Leiden University

________________________________

From: SPSSX(r) Discussion on behalf of Katina Dimoulias
Sent: Fri 16/11/2007 00:25
To: [hidden email]
Subject: Help with Categorical Principal Components Analysis



Hi all,

Firstly, thank you to Hector and Kylie for your responses to my previous
question about CATPCA .

Now I desperately need help to a use it........
I have attempted to run CATPCA on my ordinal data (I have previously run
normal factor analysis with principal components), however I am getting a
long list of warnings -  I have no knowledge or understanding about what I
am doing, the correct choices to make in the procedure and how to interpret
the output.  Can anyone help me by pointing me to some literature which
will give me this information, or similar information for CATPCA to that
which is in many SPSS texts explaining each step for Factor analysis, how
to interpret outputs etc.

Thanks,

Katina

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD



**********************************************************************
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.
**********************************************************************

====================To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD

[alexwin]

Dear Anita,

I regard methods developed by the Leiden Data Theory group as very important for social scientists and am going to teach them in one of my quantitative courses. Could you recommend books, papers or other sources in addition to the manual you mentioned?

Thank you very much in advance,

Alex

============================

Dr. Alexander Vinogradov, Associate Professor
National University "Kyiv-Mohyla Academy"
Ukraine

From: Kooij, A.J. van der
Sent: Fri 16/11/2007 00:48
To: [hidden email]
Subject: RE: Help with Categorical Principal Components Analysis



> Hi Katina,
=20
The Categories manual gives the information you are looking for; possibly (=
depending on which SPSS version you have)
it is as a pdf file in you SPSS directory. If not, search the web, it can b=
e downloaded from several sites.
An additional source of information is me (the Leiden Data Theory Group dev=
eloped the Cateogries procedures). For any questions about using and interp=
retation you can mail me. Send me the warnings you get.
=20
Kind regards,
c van der Kooij
Data Theory Group
Leiden University


=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD