I am attempting to create a logistic regression model to examine the factors
that determine the emergence of four species of aquatic invertebrates. The
invertebrates were trapped at two sites over a period of two years. The traps
were emptied on an irregular spaced basis (with an extended gap over the winter
period) and both sites were not always visited on the same day. I have two
covariates I would like to test, discharge which is the same at both sites and
temperature with is different between the sites. The main aim of the analysis
is to see whether the difference temperature regimes between the two sites
alters the probability the invertebrates will emerge. I had planned to test the
this using a GLM of the form
model1<-glm(B.rhodani_Pres ~ Temp+ Discharge + Temp:Site_Code, family =
binomial())
However examination of the Durbin Watson statistic suggests the residuals for
the four models (one for each species) are highly autocorrelated.
Does anyone have any ideas how I can incorporate the temporal autocorrelation
into the models?
Any advice would be greatly appreciated
Tom
[[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.
