Hi all,
I am using the negative binomila glm in MASS. This is my data alled data1:
Reps Treats counts
HSM1 1 0 21
HSM2 2 0 34
HSM3 3 0 27
PTM1 1 1 32
PTM2 2 1 20
PTM3 3 1 23
I goal is to do a GLM to extract the p-values from Treatment. row.
However, I can access the coefficients but not the p-values.
On another note, I want to simulate from the null. Is it more appropriate to
use:
nullmodel <- glm.nb(counts~1,data=data.use)
OR
should I use: nullmodel <- glm.nb(counts~ Reps,data=data.use) instead?
FInally, if I simulate 10 data simulations of the counts, Is this the way to
store the p-values?
response.sim = simulate(nullmodel,10)
for (j in 1:10)
{
counts.null = response.sim[,j]
new.data.mat = data.frame(Reps,Treats,counts.null)
new.glm <- glm.nb(counts.null ~ Reps, data = new.data.mat)
storage.ps[j] <- 1-pchisq(new.glm$null.deviance,df=new.glm$df.null)
}
The null is there is no differences between the 2 treatments
The alternative is there is a difference between the 2 treatments.
Any help is greatly appreciated.
--
Thanks,
Jim.
[[alternative HTML version deleted]]
______________________________________________
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
