Hi,
I have confirmed temporal correlation problems in my data. Is there a
possibility to use corCompSymm for a gamm()?
I am an R-beginner.
I have very short time series. There are three years and within each year,
there are 10 weeks. he 10 weeks are the same every year and have not unique
values, I seem not to be able to use AR-1 (I assume that I have too little
data for autoregression models of higher orders (ARMA)). If I rename weeks
as week 1-week 30 to get unique identifiers, I loose the seasonal and
year-specific effect in the final model.
M2c.gamm <- gamm(het ~ s(LN.DIN, k=3) + s(LN.totn, k=3) + s(Ncell,
k=3) + s(LN.biom) + s(temp, k=3) + s(week, k=3)
+ fstation + fyear, method = "ML",
weights = varIdent(form=~1 | fstation),
data = data1,
correlation = corCompSymm(form = ~ week|year)) #seems not to work in
a gamm()
Thank you for your time!
Anna Zakrisson Braeunlich
PhD Student
Department of Systems Ecology
Stockholm University
Svante Arrheniusv. 21A
SE-106 91 Stockholm
E-mail: a...@ecology.su.se
Tel work: +46 (0)8 161103
Mobile: +46-(0)700-525015
Web site: http://www.ecology.su.se/staff/personal.asp?id=163
><((((º>`â¢. . ⢠`â¢. .⢠`â¢. . ><((((º>`â¢. . ⢠`â¢. .â¢
`â¢. .><((((º>
[[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.
