query on binomial glm of pollination experiment

classic Classic list List threaded Threaded
1 message Options
Reply | Threaded
Open this post in threaded view
|

query on binomial glm of pollination experiment

Mariano Devoto
Dear all,

I am trying to assess the effect of five pollination treatments on a
plant's fruit set. The data set is not too good (few samples and unbalanced
-we lost many field samples to vandalism-, quite a few zeros). I counted
the n of flowers that received each treatment and the number of fruits at
the end of the experiment. I am using a binomial model, but the results
look awkward (from looking at the data I would expect *some*
significant effect).
I'll be grateful for any advice on how to reliably test the significance of
the treatments and do multiple pairwise comparisons.
Thanks in advance for your help!

Here is the code to load the data and perform the analysis. I've attached
the dataset.

#loading data
sistrep <- read.table('articulata.csv', sep=",", head=T)
str(sistrep)
nofruits <- sistrep$flowers - sistrep$fruits

#this bit plots the data
prop <- sistrep$fruits/sistrep$flowers
boxplot(prop ~ treatment, data=sistrep, las=1, ylab="Fruit set (n fruits/n
flowers)", boxwex=0.6)

#and here is the model
M1 <- glm(cbind(fruits, nofruits) ~ treatment, data = sistrep, family =
"binomial")
summary(M1)



---------------------------------------------
Dr. Mariano Devoto

Profesor Adjunto - Cátedra de Botánica General, Facultad de Agronomía de la
UBA
Investigador Adjunto del CONICET

Av. San Martín 4453 - C1417DSE - C. A. de Buenos Aires - Argentina
+5411 5287-0069
*https://www.researchgate.net/profile/Mariano_Devoto
<https://www.researchgate.net/profile/Mariano_Devoto>*
_______________________________________________
R-sig-ecology mailing list
[hidden email]
https://stat.ethz.ch/mailman/listinfo/r-sig-ecology