[R] please help with estimation of true correlations andreliabilities

John Fox jfox at mcmaster.ca
Thu May 13 20:02:55 CEST 2004


Dear Jens,

If you're willing to assume multinormality but don't have in mind a
specific model to estimate, then why not use factanal? The uniquenesses
are estimates of the unreliability of the items.

I hope this helps,
 John

On Thu, 13 May 2004 17:09:14 +0200 (MEST)
 "Jens Oehlschlägel" <joehl at gmx.de> wrote:
> 
> Dear John,
> Dear Joseph,
> 
> Thank you for your quick answers and the pointer to semnet. 
> I try to clarify on my assumptions:
> 
> - yes, I am willing to assume multivariate normality
> - no, I don't want to assume a single factor model
> - I assume there is an unknown number of factors, and I do not know
> which
> items belong to which factors
> 
> but I still want to estimate single item reliabilities
> 
> Is this impossible?
> How can one specify such unspecified model to sem?
> Which (exploratory?) function would me help doing this?
> Or just: what should I read?
> 
> Thanks for any help
> 
> 
> Jens Oehlschlägel
> 
> --
> 
> ______________________________________________
> R-help at stat.math.ethz.ch mailing list
> https://www.stat.math.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/




More information about the R-help mailing list