Displaying 2 results from an estimated 2 matches for "devcrit".
2001 Aug 21
2
Problem using GLM in a loop
Hello,
I am try to perform a modeling which is relevant in a strongly
heteroscedastic context.
So I perform a dual modeling (modeling of both mean and variance of a
response) in using the following loop:
jointmod <- function(formula, data, itercrit=10,devcrit=0.0001)
{
#
# Init step
#
init <- glm(formula=formula,family=gaussian, data=data)
response <- resid(init,type="response") + predict(init,type="response")
mu <- predict(init,type="response")
iter <- 1
dev <- init$deviance
if (dev != 0) vardev <- 1
else...
2001 Aug 21
0
Re: [R] Problem using GLM in a loop (fwd)
...te:
> Hello,
>
> I am try to perform a modeling which is relevant in a strongly
> heteroscedastic context.
> So I perform a dual modeling (modeling of both mean and variance of a
> response) in using the following loop:
>
> jointmod <- function(formula, data, itercrit=10,devcrit=0.0001)
> {
> #
> # Init step
> #
> init <- glm(formula=formula,family=gaussian, data=data)
> response <- resid(init,type="response") + predict(init,type="response")
> mu <- predict(init,type="response")
> iter <- 1
> dev <- in...