Re: [R] SEM with dichotomous indicators

From: John Fox <jfox_at_mcmaster.ca>
Date: Mon 17 Oct 2005 - 07:50:01 EST


Dear Renata,

You can do this by combining the sem() and boot.sem() functions in the sem package with hetcor() in the polycor package; boot.sem() computes standard errors for parameter estimates by bootstrapping.

See ?boot.sem for an example of a confirmatory factor-analysis model with ordinal indicators. See ?sem for many examples of structural-equation models with latent variables. Just combine the two. Note that a dichotomous indicator is in effect a two-category ordinal variable and may be handled as such. For example, the polychoric correlation between two dichtomous variables is just their tetrachoric correlation.

I hope this helps,
 John

On Mon, 10 Oct 2005 11:23:25 -0300
 "Renata" <renata@lipe.com.br> wrote:
> Hello,
>
>
>
> I'd like to know if there is a way to fit a Structural equation model
> with
> dichotomous indicators (ex: problem with a phone solved/ or not)
> having
> effects on a ordinal variable.
>
> How I do that using R?
>
> Do you have an example with the code in R that you can send to me?
>
>
>
> Thanks a lot!
>
> Renata Estrella
>
> UFRJ, Brasil, Rio de Janeiro
>
>
>
>
>
> Renata Leite Estrella
>
> Assistente de Pesquisa
>
> (21) 3978-8888 Ramal 8841
>
> www.lipe.com.br
>
>
>
>
> [[alternative HTML version deleted]]
>
> ______________________________________________
> R-help@stat.math.ethz.ch mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide!
> http://www.R-project.org/posting-guide.html



John Fox
Department of Sociology
McMaster University
Hamilton, Ontario, Canada
http://socserv.mcmaster.ca/jfox/

R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html Received on Mon Oct 17 07:53:44 2005

This archive was generated by hypermail 2.1.8 : Sun 23 Oct 2005 - 18:58:39 EST