[R] binary data with correlation

[yvonne fabian]

Dear posters,
I have a question concerning binary data analysis. I have presence absence
data of 5 sampling sessions within 3 years, of 12 fields. Each field had 12
traps. I would like to analyse the data with a Generalized Estimating
Equations (GEE) Model in R. For the abundance data I used a gls with the
function: 
correlation = corARMA(form = ~ session|trapfield, p = 1, q = 0)

But now I want to use presence absence data…I know about the problem with
correlated -binary data- but maybe somebody already created a solution?
Something like that, which is not working….

rgee1 <- geeglm(Alus01 ~ treatment + scale(LAI) + scale(log(Tot_Sp)) +
scale(AveH) , data = plates, family = binomial, waves = session, id =
trapfield, corstr = "ar1")

Any help is appreciated a lot….
Thanks
Yvonne


--
View this message in context: http://r.789695.n4.nabble.com/binary-data-with-correlation-tp3393884p3393884.html
Sent from the R help mailing list archive at Nabble.com.