Hello all,
I'm an R novice, recently trying to implement R in my research. Using the
data frame below, I want to construct a repeated measures model, with energy
expenditure (kjday) as dependent of treatment (code)
using mass as a covariate.
ind mass kjday code
79 15.8 45.216 3
42 16.5 44.64 3
10 14.85 45.216 3
206 15.75 45.216 3
23 12.15 42.336 3
5 14.6 51.264 3
....
79 16.9 46.944 5
42 16.6 44.352 5
10 15.6 51.552 5
206 15.5 45.504 5
23 12.3 42.336 5
5 13.9 42.624 5
I'm not all to sure on how to perform the analysis, but I've used the
follwing code:
> library(nlme)
> summary(lme(kjday~code+mass,random=~1|ind))
To generate the following output:
Linear mixed-effects model fit by REML
Data: NULL
AIC BIC logLik
119.5274 124.75 -54.7637
Random effects:
Formula: ~1 | ind
(Intercept) Residual
StdDev: 0.0001336186 2.578544
Fixed effects: Kjday28 ~ code + mean.mass
Value Std.Error DF t-value p-value
(Intercept) 33.25184 6.123011 11 5.430634 0.0002
code -0.10226 0.526522 10 -0.194218 0.8499
mean.mass 0.85440 0.387132 10 2.206988 0.0518
Correlation:
(Intr) code
code -0.319
mean.mass -0.935 -0.026
Standardized Within-Group Residuals:
Min Q1 Med Q3 Max
-1.0292955 -0.4640126 -0.2943731 0.1448909 2.2666898
Number of Observations: 24
Number of Groups: 12
Am I on the right track here? If so, would I be able to use the same code on
a repeated model with
more covariates, looking something like "energy
expenditure~temperature+treatment(2 levels)+mass" again including "subject"
as a random factor.
Best regards,
Andreas Nord
--
View this message in context:
http://www.nabble.com/Help-with-repeated-measures%21-tf4634251.html#a13233742
Sent from the R help mailing list archive at Nabble.com.
______________________________________________
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.
