Hi,
I'm using the SEM package to estimate a model with a binary variabele as
dependent variable.
In the literature I have to use then the correlation matrix, made by
function hetcor(). Literature also says that the standard errors are not
correct then.
My question is if somebody knows what the impact is on the estimated
coefficients.
If I want to calculate the estimated probability I see a large difference
if I'm using the covariance-matrix of the correlation-matrix. And I'm
wondering if this is because of the standard errors.
I hope somebody can help me.
Best,
Tryntsje
[[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.
