I am a new R user but a long time SAS user. I searched for a response to this question but no luck, so forgive me if this topic has been covered before. I am running a TukeyHSD post hoc test after running an ANOVA. I get the results of all pairwise comparisons, no problem. However, the output table is a little "busy", and I'd like to make the output easier to read. Specifically, I would like all groups which are not significantly different to be given the same letter. For example, here is a simple ANOVA with Tukey post hoc. It compares weight gain in pigs among 4 feeds labeled "A", "B", "C", and "D":> a = aov(Weight~Feed) > TukeyHSD(a)Tukey multiple comparisons of means 95% family-wise confidence level Fit: aov(formula = Weight ~ Feed) $Feed diff lwr upr p adj B-A 6.68 1.096263 12.263737 0.0168421 C-A 8.73 2.807553 14.652447 0.0034914 D-A -1.38 -6.963737 4.203737 0.8906642 C-B 2.05 -3.872447 7.972447 0.7530266 D-B -8.06 -13.643737 -2.476263 0.0041505 D-C -10.11 -16.032447 -4.187553 0.0009497 What I really want would look something like this: Feed Mean TukeyResult C 73.4 a B 71.3 a A 64.6 b D 63.2 b Any ideas? [[alternative HTML version deleted]]
install.packages('sos' ) # if you do not have it already
library(sos)
hsd <- ???TukeyHSD # 27 matches
summary(hsd) # in 12 packages
hsd # open the results in a browser.
# Note especially the second package multcompView
# The multcomp package with 2 matches has a companion book
# Frank Bretz, Torsten Hothorn and Peter Westfall (2010), Multiple
Comparisons Using R, CRC Press, Boca Raton.
Hope this helps.
Spencer Graves
On 10/21/2010 7:50 PM, Timothy Spier wrote:> I am a new R user but a long time SAS user. I searched for a response to
this question but no luck, so forgive me if this topic has been covered before.
I am running a TukeyHSD post hoc test after running an ANOVA. I get the results
of all pairwise comparisons, no problem. However, the output table is a little
"busy", and I'd like to make the output easier to read.
Specifically, I would like all groups which are not significantly different to
be given the same letter.
>
> For example, here is a simple ANOVA with Tukey post hoc. It compares weight
gain in pigs among 4 feeds labeled "A", "B", "C",
and "D":
>
>> a = aov(Weight~Feed)
>> TukeyHSD(a)
> Tukey multiple comparisons of means
> 95% family-wise confidence level
>
> Fit: aov(formula = Weight ~ Feed)
>
> $Feed
> diff lwr upr p adj
> B-A 6.68 1.096263 12.263737 0.0168421
> C-A 8.73 2.807553 14.652447 0.0034914
> D-A -1.38 -6.963737 4.203737 0.8906642
> C-B 2.05 -3.872447 7.972447 0.7530266
> D-B -8.06 -13.643737 -2.476263 0.0041505
> D-C -10.11 -16.032447 -4.187553 0.0009497
>
>
>
> What I really want would look something like this:
>
> Feed Mean TukeyResult
> C 73.4 a
> B 71.3 a
> A 64.6 b
> D 63.2 b
>
>
> Any ideas?
>
> [[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.
>
>
--
Spencer Graves, PE, PhD
President and Chief Operating Officer
Structure Inspection and Monitoring, Inc.
751 Emerson Ct.
San Jos?, CA 95126
ph: 408-655-4567
Dear Timothy, Use library(agricolae)> library(agricolae) > a = aov(Weight~Feed) > HSD.test(a,"Feed")HSD.test(a,"Feed", group=TRUE) HSD.test(a,"Feed", group=FALSE) Regards, Felipe de Mendiburu. http://tarwi.lamolina.edu.pe/~fmendiburu International Potato Center. www.cipotato.org University: Agraria La Molina - Peru. www.lamolina.edu.pe -----Original Message----- From: r-help-bounces at r-project.org [mailto:r-help-bounces at r-project.org] On Behalf Of Timothy Spier Sent: Thursday, October 21, 2010 9:50 PM To: r-help at r-project.org Subject: [R] visualize TukeyHSD results I am a new R user but a long time SAS user. I searched for a response to this question but no luck, so forgive me if this topic has been covered before. I am running a TukeyHSD post hoc test after running an ANOVA. I get the results of all pairwise comparisons, no problem. However, the output table is a little "busy", and I'd like to make the output easier to read. Specifically, I would like all groups which are not significantly different to be given the same letter. For example, here is a simple ANOVA with Tukey post hoc. It compares weight gain in pigs among 4 feeds labeled "A", "B", "C", and "D":> a = aov(Weight~Feed) > TukeyHSD(a)Tukey multiple comparisons of means 95% family-wise confidence level Fit: aov(formula = Weight ~ Feed) $Feed diff lwr upr p adj B-A 6.68 1.096263 12.263737 0.0168421 C-A 8.73 2.807553 14.652447 0.0034914 D-A -1.38 -6.963737 4.203737 0.8906642 C-B 2.05 -3.872447 7.972447 0.7530266 D-B -8.06 -13.643737 -2.476263 0.0041505 D-C -10.11 -16.032447 -4.187553 0.0009497 What I really want would look something like this: Feed Mean TukeyResult C 73.4 a B 71.3 a A 64.6 b D 63.2 b Any ideas? [[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.