[R] lme output

Rachel Merriman r.cunliffe at auckland.ac.nz
Sat Aug 10 04:44:46 CEST 2002


Hi,

I am having difficulty understanding some lme output -- I haven't found too 
many examples to help explain to me how to interpret the coefficients and would 
appreciate any help.

I am fitting a model:

fit <- lme(y ~ pre + group + time + group:time, random=~1|subject, 
na.action=na.omit, data=mydata)

...for a dataset where there are two groups being followed over time.  pre is 
before the treatment, and there are 4 post-treatment times (unequally spaced). 

The fitted coefficients are:

(Intercept) pre    group2 time2  time3  time4  group2:time2 group2:time3 
group2:time4
2.6442      0.5478 1.0183 0.6085 0.2326 0.5059 -1.9177      -0.3500 
-2.2029

of which there are only significant p-values (<0.05) for (Intercept), pre, 
group2:time2 and group2:time4.

anova(fit) gives:
               numDF  denDF  F-value  p-value
(Intercept)        1    864 550.9939   <.0001
pre                1    348 129.1674   <.0001
group              1    348   0.0049   0.9444
time               3    864   0.6715   0.5697
group:time         3    864   2.7206   0.0434

What I can't seem to do is understand how to correctly interpret the 
coefficients about what is going on.  I have been trying to work out the 
coefficients by subtracting various means but am getting nowhere.

Is anyone able to give me kind hand?

Rachel

-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-help-request at stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._



More information about the R-help mailing list