[R] TukeyHSD plot error

R. Michael Weylandt michael.weylandt at gmail.com
Thu May 17 01:15:43 CEST 2012


Hmmm, I can't reproduce, but I'm not really sure why that would
happen... is there any way you can test this in a --vanilla R session?
(That's the UNIX-y way to start a totally clean session; not sure
exactly how to achieve that on Windows)

Does this happen if you just run

example(TukeHSD)

directly or only when you copy and paste the commands yourself?
Hopefully we'll be able to track this down, but my initial guess is
that it's some nasty combination of all the packages you have up.

Michael

On Wed, May 16, 2012 at 1:16 PM, Bret Jagger <cantleavethismt at gmail.com> wrote:
> Hi, I am seeking help with an error when running the example from R
> Documentation for TukeyHSD.  The error occurs with any example I run, from
> any text book or website.  thank you...
>
>> plot(TukeyHSD(fm1, "tension")).
> Error in plot(confint(as.glht(x)), ylim = c(0.5, n.contrasts + 0.5), ...) :
>  error in evaluating the argument 'x' in selecting a method for function
> 'plot': Error in UseMethod("vcov") :
>  no applicable method for 'vcov' applied to an object of class "NULL"
>
>
>> ?TukeyHSD
>> require(graphics)
>
>> summary(fm1 <- aov(breaks ~ wool + tension, data = warpbreaks))
>            Df Sum Sq Mean Sq F value  Pr(>F)
> wool         1    451   450.7   3.339 0.07361 .
> tension      2   2034  1017.1   7.537 0.00138 **
> Residuals   50 6748 135.0
> ---
> Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
>> TukeyHSD(fm1, "tension", ordered = TRUE)
>  Tukey multiple comparisons of means
>    95% family-wise confidence level
>    factor levels have been ordered
>
> Fit: aov(formula = breaks ~ wool + tension, data = warpbreaks)
>
> $tension
>         diff        lwr      upr     p adj
> M-H  4.722222 -4.6311985 14.07564 0.4474210
> L-H 14.722222  5.3688015 24.07564 0.0011218
> L-M 10.000000  0.6465793 19.35342 0.0336262
>
>> plot(TukeyHSD(fm1, "tension"))
> Error in plot(confint(as.glht(x)), ylim = c(0.5, n.contrasts + 0.5), ...) :
>  error in evaluating the argument 'x' in selecting a method for function
> 'plot': Error in UseMethod("vcov") :
>  no applicable method for 'vcov' applied to an object of class "NULL"
>>
>> sessionInfo()
> R version 2.15.0 (2012-03-30)
> Platform: i386-pc-mingw32/i386 (32-bit)
>
> attached base packages:
>  [1] grid      tcltk     splines   stats     graphics  grDevices datasets
>  utils     methods   base
>
> other attached packages:
>  [1] RcmdrPlugin.HH_1.1-30 HH_2.2-30             latticeExtra_0.6-19
> RColorBrewer_1.0-5
>  [5] leaps_2.9             multcomp_1.2-12       mvtnorm_0.9-9992
>  NADA_1.5-4
>  [9] ggplot2_0.9.0         Rcmdr_1.8-3           car_2.0-12
>  nnet_7.3-1
> [13] DAAG_1.12             survival_2.36-12      randomForest_4.6-6
>  rpart_3.1-52
> [17] RODBC_1.3-5           tree_1.0-29           spatstat_1.25-5
> mgcv_1.7-13
> [21] sciplot_1.0-9         spdep_0.5-45          coda_0.14-6
> deldir_0.0-16
> [25] maptools_0.8-14       foreign_0.8-49        nlme_3.1-103
>  MASS_7.3-17
> [29] boot_1.3-4            sp_0.9-98             odesolve_0.9-9
>  mcmc_0.8
> [33] lme4_0.999375-42      Matrix_1.0-6          lattice_0.20-6
>  chron_2.3-42
> [37] akima_0.5-7           rcom_2.2-3.1.1        rscproxy_1.3-1
>
> loaded via a namespace (and not attached):
>  [1] colorspace_1.1-1 dichromat_1.2-4  digest_0.5.2     memoise_0.1
>  munsell_0.3      plyr_1.7.1
>  [7] proto_0.3-9.2    reshape2_1.2.1   scales_0.2.0     stats4_2.15.0
>  stringr_0.6      tools_2.15.0
>
>        [[alternative HTML version deleted]]
>
>
> ______________________________________________
> R-help at 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.
>



More information about the R-help mailing list