I have to apologize, my subject was misleading or wrong.
thanks for pointing me to the correct name/description.
A goodness of fit measure for a Poisson GLM is what I am looking for.
I am looking for a method similar to cv.glm(),to receive the estimate of
prediction error.
I will have a look
Martin -
Do you want a goodness of fit measure for a Poisson glm ?
I would start py plotting the residuals and doing an
analysis of deviance on nested models. See McCullagh and
Nelder, as well as more recent references.
- tom blackwell - u michigan medical school - ann arbor -
On Fri, 2
Martin -
I can't figure out what question you are asking.
Does either predict.glm() in the base package or
cv.glm() in the boot package do what you want ?
The theory for all of this is given in the references
listed in the help pages for "glm" and "cv.glm".
- tom blackwell - u michigan
The help page for "predict" says it is a generic function. Then
command 'methods("predict")' reveals a function called "predict.glm",
which has its own help page. Does that provide what you want?
Also, I didn't find your earlier post in "www.r-project.org" ->
"search" -> "R site se
hello,
I apologize that I poste this question again but I did not receive any replies
on this topic and would like to know if the mail has been read over or if
there is no method of statistical prediction computation for poisson errors
in glm().
I am looking for a way to compute the model pr