Dear Maya,
I think that what you've done should work fine, though I'm not sure why you
created your own UNIT variable rather than allowing sem() to generate the
constant.
Best,
John
On Sat, 24 Nov 2012 10:33:50 +0200
Maya Abou Zeid <ma...@aub.edu.lb> wrote:
> Dear John,
>
> Many thanks for your response.
> I'd just still like to double check that I have indeed used the raw moment
> matrix method correctly in sem. In my model, some equations are in deviations
> form and have no intercept, while some have intercept.
>
>
> sem.QT.1 <- sem(mod.QT.1, data=QTrav, formula = ~ X1 + X2 + .... + UNIT -1,
> fixed.x=c('X1','X2',...,'UNIT'), raw=TRUE)
>
> where UNIT is a variable equal to 1 which I appended to the dataset. I used
> UNIT multiplied by a constant in the model equations that require an
> intercept.
>
> I mainly wanted to check if the above specification of formula, with -1
> written after UNIT, is correct. The model runs fine.
>
> Thank you,
> Maya
>
>
> -----Original Message-----
> From: John Fox [mailto:j...@mcmaster.ca]
> Sent: Friday, November 23, 2012 2:39 PM
> To: Maya Abou Zeid
> Cc: r-help@r-project.org
> Subject: Re: [R] SEM raw moment matrix
>
> Dear Maya,
>
> sem() computes the fit statistics that I know how to compute for a model fit
> to a raw moment matrix. If you know how to compute the others (and if they're
> defined), then you could do that youself using the object returned by sem().
>
> I'm not sure why you want the likelihood under the model in addition to the
> model chisquare, but you can get the *log*-likelihood from logLik(your.model).
>
> Finally, you don't have to compute the raw moment matrix in a separate step
> (if you in fact did that) if you have the original data -- you can use the
> data argument to sem().
>
> I hope this helps,
> John
>
> ------------------------------------------------
> John Fox
> Sen. William McMaster Prof. of Social Statistics
> Department of Sociology
> McMaster University
> Hamilton, Ontario, Canada
> http://socserv.mcmaster.ca/jfox/
>
> On Fri, 23 Nov 2012 00:33:51 +0200
> Maya Abou Zeid <ma...@aub.edu.lb> wrote:
> > Hello,
> >
> > I estimated a model using SEM package in R, which was fit to a raw moment
> > matrix, and includes an intercept term. The only goodness of fit statistics
> > that are output are Model Chisquare, AIC, AICc, BIC, CAIC, and normalized
> > residuals.
> >
> > How can I get the other goodness of fit statistics, like adjusted goodness
> > of fit, RMSEA, and R-squared? And how can I get the final value of the
> > log-likelihood of the model?
> >
> > Thanks,
> > Maya
> >
> > [[alternative HTML version deleted]]
> >
> > ______________________________________________
> > R-help@r-project.org mailing list
> > https://stat.ethz.ch/mailman/listinfo/r-help
> > PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> > and provide commented, minimal, self-contained, reproducible code.
______________________________________________
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
