[R] Conveting SAS Proc mixed to R code

[RKinzer]

I am desperate for help and thank you to everyone providing input.

I am using lme4 for a mixed linear model, and trying to replicate a SAS
analysis (see thread below).

Variables:
Dependent = logrkm; Independent = Group (Streams grouped by similarity),
Treatment (3 treatments), Stream, Time (1 or 2; before treatment and after),
Year (-8, -7,...7, 8; each yearly observation;negs before treatment and
positive after).

Design:
Blocking by stream group results in unbalanced repeated measures with 3
treatments arranged in blocks with various numbers of observations (Streams)
per treatment-block.  Stream, Group, and Year are random variables and
Treatment and Time are fixed effects.

I have tried the following code, but can't seem to replicate the SAS
results.  Please correct the model below if you see where I am wrong, I am
also open to other suggestions.      

m2<-lmer(logrkm~Treatment*Time+(Treatment|Stream:Group)+(1|Year),data=prototype)

Thank you.

--
View this message in context: http://r.789695.n4.nabble.com/Conveting-SAS-Proc-mixed-to-R-code-tp3450626p3452937.html
Sent from the R help mailing list archive at Nabble.com.