[R-sig-ME] Tukey after lme does not match
Dennis Murphy
djmuser at gmail.com
Fri Jan 6 05:36:41 CET 2012
Hi:
In addition to Dr. Robinson's comments, I would add the following:
(i) Your model specification indicates that you want random slopes for
trial by subject with correlated intercepts. Is that what you
intended?
(ii) I'm wondering why you're not treating angle as a continuous
variable and looking for potential trends in the response as a
function of angle. If you have a discernable trend, its form would be
more useful than a collection of multiple comparisons. Did you plot
the response by subject and angle (either a conditioning plot by
subject or a 'spaghetti plot' of individual profiles of (angle, RMSy)
pairs)?
My 2c,
Dennis
On Thu, Jan 5, 2012 at 4:22 PM, Alen Hajnal <Alen.Hajnal at usm.edu> wrote:
> Dear R users:
> I have a simple lme model based on the following data:
> sub trial angle RMSy
> 1 1 30 3.745084
> 1 2 0 7.520667
> 1 3 90 11.17038
> 1 4 15 7.581526
> 1 5 60 11.17822
> 1 6 75 8.440891
> 1 7 45 13.19024
> 1 8 15 9.822035
> 1 9 60 6.002665
> 1 10 75 4.393961
> 1 11 0 7.436676
>
> When I run the model the results show that 0vs45, 0vs60, 0vs75, and 0vs90 are all significant main effects:
>
>> m.base01<-lme(RMSy ~ angle+trial, data=data, random=~ trial|sub,method='ML')
>> summary(m.base01)
> Fixed effects: RMSy ~ angle + trial
> Value Std.Error DF t-value p-value
> (Intercept) 5.236020 0.6312637 267 8.294505 0.0000
> angle15 -0.687669 0.4140277 267 -1.660925 0.0979
> angle30 -0.571092 0.4129365 267 -1.383001 0.1678
> angle45 -0.984597 0.4139330 267 -2.378638 0.0181
> angle60 -0.874718 0.4135615 267 -2.115085 0.0353
> angle75 -1.389835 0.4113411 267 -3.378788 0.0008
> angle90 -1.620493 0.4133209 267 -3.920666 0.0001
> trial -0.009372 0.0299782 267 -0.312620 0.7548
>
> However, when I try to run a Tukey posthoc test, I get different results (notice that the estimates are the same as the main effect values above): ONLY 0vs90 is significant at p<.05 :
>
>> summary(glht(m.base01, linfct=mcp(angle = "Tukey")))
>
> Simultaneous Tests for General Linear Hypotheses
>
> Multiple Comparisons of Means: Tukey Contrasts
>
>
> Fit: lme.formula(fixed = RMSy ~ angle + trial, data = data, random = ~trial |
> sub, method = "ML")
>
> Linear Hypotheses:
> Estimate Std. Error z value Pr(>|z|)
> 15 - 0 == 0 -0.6877 0.4082 -1.684 0.62652
> 30 - 0 == 0 -0.5711 0.4072 -1.403 0.80077
> 45 - 0 == 0 -0.9846 0.4081 -2.412 0.19329
> 60 - 0 == 0 -0.8747 0.4078 -2.145 0.32592
> 75 - 0 == 0 -1.3898 0.4056 -3.427 0.01070 *
> 90 - 0 == 0 -1.6205 0.4075 -3.976 0.00138 **
> 30 - 15 == 0 0.1166 0.4079 0.286 0.99996
> 45 - 15 == 0 -0.2969 0.4078 -0.728 0.99090
> 60 - 15 == 0 -0.1870 0.4078 -0.459 0.99931
> 75 - 15 == 0 -0.7022 0.4050 -1.734 0.59342
> 90 - 15 == 0 -0.9328 0.4073 -2.290 0.24842
> 45 - 30 == 0 -0.4135 0.4082 -1.013 0.95124
> 60 - 30 == 0 -0.3036 0.4074 -0.745 0.98971
> 75 - 30 == 0 -0.8187 0.4052 -2.021 0.40123
> 90 - 30 == 0 -1.0494 0.4076 -2.574 0.13377
> 60 - 45 == 0 0.1099 0.4077 0.269 0.99997
> 75 - 45 == 0 -0.4052 0.4059 -0.998 0.95449
> 90 - 45 == 0 -0.6359 0.4078 -1.559 0.70835
> 75 - 60 == 0 -0.5151 0.4050 -1.272 0.86496
> 90 - 60 == 0 -0.7458 0.4074 -1.831 0.52730
> 90 - 75 == 0 -0.2307 0.4049 -0.570 0.99763
>
> Why does the Tukey not match the lme results?
> Any help would be much appreciated!
> Thanks, Alen
>
>
>
>
> ----------
> Alen Hajnal, PhD.
> Department of Psychology
> The University of Southern Mississippi
> 118 College Drive #5025
> Hattiesburg, MS 39406
> USA
> Tel. +1 (601) 266-4617
> alen.hajnal @ usm.edu
> http://ocean.otr.usm.edu/~w785427/lab.html
> _______________________________________________
> R-sig-mixed-models at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models
More information about the R-sig-mixed-models
mailing list