[R-sig-ME] nlme library

[Nilsson Fredrik X]

Hi Roberta,

Try:
m2<-m1$apVar
str(m2)
exp(attr(m2,"Pars"))
sought<-exp(attr(m2,"Pars"))[1]

Best,
Fredrik

----------------------------------------------------
Fredrik Nilsson, PhD
Competence Centre for Clinical Research
University Hospital, Lund
Tel: +46 46 177987
Fax: +46 46 176085

-----Ursprungligt meddelande-----
Från: r-sig-mixed-models-bounces at r-project.org [mailto:r-sig-mixed-models-bounces at r-project.org] För roberta varriale
Skickat: den 25 juni 2008 11:23
Till: r-sig-mixed-models at r-project.org
Ämne: [R-sig-ME] nlme library

Hello,
I'm Roberta.
I'm working with R since some months, but I still have some problems.
At the moment I'm using the library nlme, in particular the function
lme and I have a question.

Just as an example I write the code:
library(nlme)
library(SASmixed)
data(Mississippi)
m1 <- lme(y ~ 1, data = Mississippi, random = ~ 1|influent)
summary(m1)


and I obtain these results:

Linear mixed-effects model fit by REML
 Data: Mississippi
       AIC      BIC    logLik
  258.3511 263.1017 -126.1756

Random effects:
 Formula: ~1 | influent
        (Intercept) Residual
StdDev:    7.957598 6.531317

Fixed effects: y ~ 1
               Value Std.Error DF  t-value p-value
(Intercept) 21.22312  3.429034 31 6.189241       0

Standardized Within-Group Residuals:
        Min          Q1         Med          Q3         Max
-1.91443594 -0.53645956 -0.03217348  0.83713515  1.95823685

Number of Observations: 37
Number of Groups: 6


Now, I would like to recall the parameter "Random effects StdDev
(Intercept)", equal to 7.957598, but I'm not able to find its "R-name".
I read the Documentation on R web site and I found the "name" of other
parameters (such as ...$coeff$fixed and ...$sigma) but I really need that
one.
Someone can help me, please?

Thanks in advance,
best regards,
Roberta Varriale

	[[alternative HTML version deleted]]

_______________________________________________
R-sig-mixed-models at r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models