[R] R interpretation

From: dan kumpik <daniel.kumpik_at_physiol.ox.ac.uk>
Date: Mon 22 Jan 2007 - 20:10:24 GMT


Hi,

I am new to R (and not really a stats expert) and am having trouble interpreting its output. I am running a human learning experiment, with 6 scores per subject in both the pretest and the posttest. I believe I have fitted the correct model for my data- a mixed-effects design, with subject as a random factor and session (pre vs post) nested within group (trained vs control).

I am confused about the output. The summary command gives me this table:

> D.lme<- lme(score~GROUP/session, random=~1|subject, data=ILD4L )
> summary(D.lme)

Linear mixed-effects model fit by REML

   Data: ILD4L
    Subset: EXP == "F"

          AIC BIC logLik
    -63.69801 -45.09881 37.84900

Random effects:

   Formula: ~1 | subject

          (Intercept) Residual
StdDev: 0.1032511 0.1727145

Fixed effects: score ~ GROUP/session

                           Value  Std.Error  DF   t-value p-value
(Intercept)         0.10252778 0.05104328 152  2.008644  0.0463
GROUPT              0.09545347 0.06752391  12  1.413625  0.1829
GROUPC:sessionpost -0.00441389 0.04070919 152 -0.108425 0.9138 GROUPT:sessionpost -0.23586042 0.03525520 152 -6.690090 0.0000

   Correlation:

                     (Intr) GROUPT GROUPC
GROUPT             -0.756

GROUPC:sessionpost -0.399 0.301
GROUPT:sessionpost 0.000 -0.261 0.000

Standardized Within-Group Residuals:

          Min Q1 Med Q3 Max -2.66977386 -0.52935645 -0.08616759 0.57215015 3.26532101

Number of Observations: 168
Number of Groups: 14

I believe the fixed-effects section of this output to be telling me that my model intercept (which I assume to be the control group pretest?) is significantly different from 0, and that GROUPT (i.e. the trained group) does not differ significantly from the intercept- therefore no pretest difference between groups?

        The next line is, I believe showing that the GROUPC x sessionpost interaction (i.e., control posttest scores?) is not significantly different from the intercept (i.e. control pretest scores). Finally, I am interpreting the final line as indicating that the GROUPT x sessionpost interaction (ie, trained posttest scores?) is significantly different from the trained pretest scores (GROUPT). A treatment contrast that I would like to apply would be for Control-post vs Trained-post, to see if the groups differ after training, but I'm not sure how to do this- and I feel I am probably overcomplicating the matter.

also,
I am confused about how to report this output in my publication. For instance, what should I be reporting for df? Those found on the output of the anova table?

Would it be possible to look through this for me and indicate how to interpret the R output, and also how I should be reporting this? Apologies for asking such basic questions, but I would like to start using R more regularly and to make sure I am doing so correctly.

Many thanks,

Dan



R-help@stat.math.ethz.ch 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. Received on Tue Jan 23 07:16:57 2007

Archive maintained by Robert King, hosted by the discipline of statistics at the University of Newcastle, Australia.
Archive generated by hypermail 2.1.8, at Mon 22 Jan 2007 - 20:30:38 GMT.

Mailing list information is available at https://stat.ethz.ch/mailman/listinfo/r-help. Please read the posting guide before posting to the list.