[R] continuous independent variable in lme
Federico Calboli
f.calboli at ucl.ac.uk
Mon Jul 28 00:58:52 CEST 2003
At 14:14 27/07/2003 +0100, you wrote:
>Your anova call is a sequential anova, which you are misinterpreting.
>You can't conclude terms are significant or not if later terms are.
>You need to use type="marginal" to interpret things the way you do (except
>that I hope that does not drop the main effect and keep the interaction).
>
>You also seem to be interpreting main effects in the presence of
>interactions incorrectly. In your first model the coefs for `line' are
>intercepts at 0 temp (probably uninteresting) whereas in the second they
>are at intercepts at temp=21.5 (probably also uninteresting). It makes
>perfect sense to have lines of different slopes with similar intercepts at
>0 but different ones at 21.5.
>
>Perhaps it is `temp' you want to think hard about how to code?
Prof. Ripley,
many thanks for your reply. I coded temperature as a factor and imposed the
contrasts:
[,1]
18 1
25 -1
After doing this, the results of anova() are the following:
anova(lme(area ~line*temp, random= ~ 1|replicate/temp, mydata), type="m")
numDF denDF F-value p-value
(Intercept) 1 336 41817.83 <.0001
line 3 8 14.38 0.0014
temp 1 8 338.21 <.0001
line:temp 3 8 0.62 0.6211
which, incidentally, are identical to the call:
anova(lme(area ~line*temp, random= ~ 1|replicate/temp, mydata))
numDF denDF F-value p-value
(Intercept) 1 336 41817.83 <.0001
line 3 8 14.38 0.0014
temp 1 8 338.21 <.0001
line:temp 3 8 0.62 0.6211
as my data is perfectly balanced (at lest I think this is the most
plausible explanation).
The contrasts read:
Value Std.Error DF t-value p-value
(Intercept) 109207.89 534.0393 336 204.49409 <.0001
line1 4704.14 755.2457 8 6.22862 0.0003
line2 -544.76 755.2457 8 -0.72130 0.4913
line3 -1043.87 534.0393 8 -1.95467 0.0864
temp1 9150.37 497.5610 8 18.39045 <.0001
line1:temp1 -337.37 703.6576 8 -0.47946 0.6444
line2:temp1 -335.11 703.6576 8 -0.47623 0.6466
line3:temp1 -589.91 497.5610 8 -1.18561 0.2698
which is what I would expect from eyeballing the interaction.plot. I
imagine I could come up with a better model, but I still need more
pondering over chpt 6 of MASS. Nonetheless I think I have a better grasp of
what I am doing now.
Regards,
Federico Calboli
=========================
Federico C.F. Calboli
Department of Biology
University College London
Room 327
Darwin Building
Gower Street
London
WClE 6BT
Tel: (+44) 020 7679 4395
Fax (+44) 020 7679 7096
f.calboli at ucl.ac.uk
More information about the R-help
mailing list