[R] variance of model delta glm

[Melen]

hi everybody,

i know it a quite complicate subject but someone might have the
solution.

I am doing a delta model coupling a binomial glm and a lognormal one.
Using the Laurent correction I can predict mean values and I would
like to know if you know how to predict the variance?

Do you know the true formula and the good code for it?

Thanks in advance
Melen