[R] how to calculate standard error for the predicted value from geeglm?

[Uwe Ligges]

On 21.02.2011 10:23, AB29 wrote:
>
> Dear Sue,
>
> I am also having problems with this. As far as I can gather the predict
> function will work with geeglm to give you predicted values from the model
> but it does not produce the standard errors automatically.
>
> I have posted a similar question and have had no answers. However, I know
> that there must be a way to do this?!
>
> Did you manage to find the answer? Or can anybody else help?
>
> Thanks
>
> Anna



Please note this is a mailing list in the first place and readers of the 
list really do not know what you are referring to.
If you want to contact "Sue", please do so and don't write to the lsut.

Thanks,
Uwe Ligges