Dear list members,
I am fitting a logistic regression with 5 explanatory factors (which I
converted to factors):
mod6 = glm(condicion ~ iluminacion + animales + cielo.raso + piso +
paredes, family=binomial, data=reglog)
I want to obtain the predicted probabilities and the se using the
func
Hi Manuel, your problem is that the new variables you created are of numeric
type, while the model was fitted using factor. So the fix is to convert the
new variables to factors so the type matchs
Luciano
2010/7/7 Manuel Spínola
> Dear list members,
>
> I am fitting a logistic regression with 5
On Wed, 2010-07-07 at 20:44 -0300, Luciano Selzer wrote:
> Hi Manuel, your problem is that the new variables you created are of numeric
> type, while the model was fitted using factor. So the fix is to convert the
> new variables to factors so the type matchs
It may need more than that; not tested
...ben bolker's glmm wiki has several examples (in faqs and
"owl"-example) how to get model predictions and se's by the use of the
model- and var/covar-matrices.
best,
kay
and Zitat von Gavin Simpson :
On Wed, 2010-07-07 at 20:44 -0300, Luciano Selzer wrote:
Hi Manuel, your problem is t