[R] SEM modelling

[John Fox]

Dear Simo,

Apparently the input covariance matrix is a list rather than a numeric
matrix. Without the input that you specified, it's not possible to know for
sure what you did, but I suspect that you used the object returned by
hetcor() in the polycor package rather than the polychoric correlation
matrix extracted from this object -- i.e., object$correlations.

I hope this helps,
 John


> -----Original Message-----
> From: r-help-bounces at r-project.org [mailto:r-help-bounces at r-project.org]
On
> Behalf Of Simo Vundla
> Sent: May-25-09 10:12 AM
> To: r-help at r-project.org
> Subject: [R] SEM modelling
> 
> Dear All,
> 
> I am trying to run a program using SEM and the input data is a covariance
> matrix (polychoric correlations). However I get an error message which
says:
> 
>                            is.triangular(S) : (list) object cannot be
coerced
> to 'double'
> 
> Do not know what the problem is. Have done something almost similar
without
> any problems.
> 
> Thanks very much
> 
> Simo
> 
> 
> 
> 	[[alternative HTML version deleted]]