Hello,
I am working on my thesis and can't really figure out how to produce a
reasonable graph from the output from my glm.,
I could just give the R-output in my results and then discuss them, but it
would be more interesting if I could visualise what is going on.
My research is how bees react to different fieldmargins, for this I have 4
different types of field margin (A,B,C & D) and two different experiments,
one where the field margins are adjecent and one where they are seperated.
I wanted to know if the bees react differently on the different types of
field margin and whether there were differences between the two
experiments... I also used an offset function to correct for the different
number of field margins of the same type were the counts have been going on.
I counted the counts of the same fied margins together and then put in the
offset function.
So i used the model that is underneath: mengsel A, B, C & D=type of field
margin and proefopzet 1 and 2= experiment p1 and p2
I already checked if this saturated model is better then that without an
interaction effect:
so I think i have a good model for my data
Call:
glm(formula = count ~ mengsel * proefopzet, family = poisson,
data = a.data, offset = log(opp))
Deviance Residuals:
[1] 0 0 0 0 0 0 0 0
Coefficients:
Estimate Std. Error z value Pr(>|z|)
(Intercept) 5.01507 0.04704 106.622 < 2e-16 ***
mengselB 0.82654 0.05640 14.656 < 2e-16 ***
mengselC -1.36441 0.12329 -11.067 < 2e-16 ***
mengselD -2.30702 0.18854 -12.237 < 2e-16 ***
proefopzetp2 -0.92909 0.10303 -9.017 < 2e-16 ***
mengselB:proefopzetp2 0.14373 0.13399 1.073 0.283411
mengselC:proefopzetp2 -2.02842 0.52307 -3.878 0.000105 ***
mengselD:proefopzetp2 3.03323 0.22821 13.291 < 2e-16 ***
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
(Dispersion parameter for poisson family taken to be 1)
Null deviance: 1.8216e+03 on 7 degrees of freedom
Residual deviance: -1.2212e-14 on 0 degrees of freedom
AIC: 67.589
Number of Fisher Scoring iterations: 3
>
Now...how can i visualise this? I don't seem to find how i could do this...
The data on which this is computed is the following:
> a.data
count proefopzet mengsel opp
1 1033 p1 B 3
2 77 p1 C 2
3 452 p1 A 3
4 30 p1 D 2
5 157 p2 B 1
6 4 p2 C 2
7 119 p2 A 2
8 123 p2 D 1
Thanks,
Babs
--
View this message in context:
http://r.789695.n4.nabble.com/producing-a-graph-with-glm-poisson-distributed-respons-count-data-and-categorical-independant-variabs-tp4638110.html
Sent from the R help mailing list archive at Nabble.com.
______________________________________________
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.
