R Extension Command that performs EFA based on Tetrachoric Correlation Coeffients

[E. Bernardo]

Hi Jon Peck and all,

Where can I download your R Extension Command that performs EFA based on Tetrachoric correlation coefficients? I will use it to perform EFA for my dichotomous variables.

Or are there SPSS macros available?

Thank you.

Eins

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

[Bruce Weaver]

Here's another (non-R) option to explore:

   http://www.ncbi.nlm.nih.gov/pubmed/22477439

It's been a while since I looked at it.  IIRC, the coding is a bit awkward (e.g., instead of using macro arguments, users must modify values in the macro definition).  But I think the results it generates are probably okay.

The same authors have also recently published SPSS syntax to compute polychoric correlations, by the way.

   http://www.ncbi.nlm.nih.gov/pubmed/25123909

HTH.

E. Bernardo wrote

Hi Jon Peck and all,
Where can I download your R Extension Command that performs EFA based on Tetrachoric correlation coefficients? I will use it to perform EFA for my dichotomous variables.
Or are there SPSS macros available?
Thank you.Eins


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

[David Marso]

Re Link 2.
Where in blazes did I leave my grapefruit spoon?
To say that code is a 'bit awkward' is well, (there is such a thing as parameterized macros.  One can define submacros in MATRIX which can serve as parameterized functions.  Authors should rewrite that mess and retract the original.  Quite messy and amateurish and that is being charitable.  If they have a grant and want to pay me I would be happy to oblige.
--

Bruce Weaver wrote

Here's another (non-R) option to explore:

   http://www.ncbi.nlm.nih.gov/pubmed/22477439

It's been a while since I looked at it.  IIRC, the coding is a bit awkward (e.g., instead of using macro arguments, users must modify values in the macro definition).  But I think the results it generates are probably okay.

The same authors have also recently published SPSS syntax to compute polychoric correlations, by the way.

   http://www.ncbi.nlm.nih.gov/pubmed/25123909

HTH.

E. Bernardo wrote

Hi Jon Peck and all,
Where can I download your R Extension Command that performs EFA based on Tetrachoric correlation coefficients? I will use it to perform EFA for my dichotomous variables.
Or are there SPSS macros available?
Thank you.Eins


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