[R] Multiple Comparison Kruskal-Wallis Test on a dataframe

2013-07-02 Thread Tom Oates
Hi I have a dataframe of genomic positions something like below: chrstartendstrand1a2a3a1b2b3b1c 2c3c1d2d3d chr1201199522201199523-516263465358 537837276562 chr120119958420119958

[R] multiple comparison tests using medians

2012-07-30 Thread Data Analytics Corp.
Hi, A client has asked for a series of pair-wise tests similar to Tukey's but using medians as opposed to means. The reason is that the distributions are highly right skewed. Are there such tests (I'm finding nothing) and if so, is there anything in R? Thanks, Walt __

Re: [R] multiple comparison of interaction of ANCOVA

2011-12-13 Thread Jinsong Zhao
Thank you very much for the suggestions. On 2011-12-13 3:20, Richard M. Heiberger wrote: ... On Mon, Dec 12, 2011 at 7:00 AM, Jinsong Zhao mailto:jsz...@yeah.net>> wrote: Apart from the data set here, is there a way to do multiple comparison on the interaction of one way analysis of co

Re: [R] multiple comparison of interaction of ANCOVA

2011-12-12 Thread Richard M. Heiberger
... On Mon, Dec 12, 2011 at 7:00 AM, Jinsong Zhao wrote: > Apart from the data set here, is there a way to do multiple comparison on > the interaction of one way analysis of covariance? > Interaction in ancova usually means the slopes are different. ... BTW, when loading HH package, the TukeyH

Re: [R] multiple comparison of interaction of ANCOVA

2011-12-12 Thread Jinsong Zhao
On 2011-12-12 1:48, Richard M. Heiberger wrote: Thank you for you use of HH. I think the right graph for this data is the much simpler ancova function library(HH) ancova(y ~ year * Trt, data=mydata) where we see that the three treatments have totally different slopes. Thank you very much for t

Re: [R] multiple comparison of interaction of ANCOVA

2011-12-12 Thread Jinsong Zhao
On 2011-12-11 22:49, Bert Gunter wrote: Inline below. -- Bert Graph the data sensibly to figure out what's going on. Statistical machinationsand anova tables with P values alone are not sufficient and can be opaque or misleading. If you do not know what "sensibly" is (or even if you do), consul

Re: [R] multiple comparison of interaction of ANCOVA

2011-12-11 Thread Richard M. Heiberger
Thank you for you use of HH. I think the right graph for this data is the much simpler ancova function library(HH) ancova(y ~ year * Trt, data=mydata) where we see that the three treatments have totally different slopes. The WoodEnergy example doesn't apply here. The WoodEnergy example illus

Re: [R] multiple comparison of interaction of ANCOVA

2011-12-11 Thread Bert Gunter
Inline below. -- Bert On Sun, Dec 11, 2011 at 4:15 AM, Jinsong Zhao wrote: > Hi there, > > The following data is obtained from a long-term experiments. > >> mydata <- read.table(textConnection(" > +        y year Trt > +     9.37 1993   A > +     8.21 1995   A > +     8.11 1999   A > +     7.22 2

[R] multiple comparison of interaction of ANCOVA

2011-12-11 Thread Jinsong Zhao
Hi there, The following data is obtained from a long-term experiments. > mydata <- read.table(textConnection(" +y year Trt + 9.37 1993 A + 8.21 1995 A + 8.11 1999 A + 7.22 2007 A + 7.81 2010 A +10.85 1993 B +12.83 1995 B +13.21 1999 B +

Re: [R] Multiple comparison test about whole population, not about mean

2011-11-02 Thread Bert Gunter
1. I found the post incoherent. 2. This appears to have nothing to do with R -- post elsewhere, e.g. http://stats.stackexchange.com/ -- Bert On Wed, Nov 2, 2011 at 10:47 AM, Serge-Étienne Parent wrote: > Multiple comparison tests are usually used to compare groups based on the > confidence regio

[R] Multiple comparison test about whole population, not about mean

2011-11-02 Thread Serge-Étienne Parent
Multiple comparison tests are usually used to compare groups based on the confidence region about the mean. Some great packages, like agricolae, proposes grouping information based on statistical tests. I am looking for a way to perform such a test, but based on the confidence region about the whol

Re: [R] Multiple comparison test on selected contrasts

2011-07-19 Thread B Jessop
; To: r-help@r-project.org > Date: Sun, 17 Jul 2011 21:04:51 -0300 > Subject: [R] Multiple comparison test on selected contrasts > > > > > > Dear Help-list, How can I do a multiple comparison test (mct) on selected > contrasts from a linear model while using packages lme

[R] Multiple comparison test on selected contrasts

2011-07-17 Thread B Jessop
Dear Help-list, How can I do a multiple comparison test (mct) on selected contrasts from a linear model while using packages lme4 and multcomp? I am running R 2.13.0 under Windows 7. The following linear model and mct produces a global mct of 15 paired contrasts of the combined (Site, Posi

[R] multiple comparison correction

2010-10-11 Thread Jake Kami
dear list, i just found this post in the archive: On 23-Apr-05 Bill.Venables at csiro.au wrote: >:* -Original Message-*>:* From: r-help-bounces at stat.math.ethz.ch > *>:* [mail

Re: [R] Multiple comparison test split plot analysis in R

2009-10-26 Thread Richard M. Heiberger
Please see the maiz example in ?HH:::glht.mmc You may need to install HH first with install.packages("HH") __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/post

[R] Multiple comparison test split plot analysis in R

2009-10-26 Thread Jo Stringer
Hi all! I have a split plot analysis in which the model parameters are: Efficacy = y Rep = block Product and rateind = main plot Variety = subplot I can do the split plot analysis with: summary(model1<-aov(efficacy~rep+product*rateind*variety+Error(rep:product:rate), data=ht28)) How do

[R] multiple comparison of means with glm model

2009-10-15 Thread Wade Wall
Hi all, I have a data set that I am analyzing and I am trying to do a multiple comparison of means under a glm model. The factors are 2 light treatments and 3 temperature treatments in a complete block design analyzed using a glm. My question is how do I do a multiple comparison of means using t

Re: [R] Multiple comparison on lme model with 2 fixed factors

2009-08-18 Thread Billeke
Sorry to come back again, but with this and other (real) data, I'm not able to obtain those comparisons. I'm using the following command and obtain the following result (lmer model). glht(lmelac.ex, linfct = mcp("ath1:tim20 - ath1:tim40 = 0"="Tukey"))->comp Erreur dans mcp2matrix(model, linfct =

Re: [R] Multiple comparison on lme model with 2 fixed factors

2009-08-18 Thread Billeke
Hi again, Reproducing part of my data (which indeed are here well standardized), I obtain similar results (with regard to the R output) than previously. These are "part" of an experimentation where people with different athletic (ath) training exercised during 120 minutes. Plasma lactate was one

Re: [R] Multiple comparison on lme model with 2 fixed factors

2009-08-18 Thread Dieter Menne
Billeke wrote: > > Reproducing part of my data (which indeed are here well standardized), I > obtain similar results (with regard to the R output) than previously. > > These are "part" of an experimentation where people with different > athletic (ath) training exercised during 120 minutes. Pla

Re: [R] Multiple comparison on lme model with 2 fixed factors

2009-08-18 Thread Dieter Menne
Billeke wrote: > > > mult2 <- glht(lmelac.ex, linfct = mcp("ath:time" = "Tukey")) > > I don't have the time to check, but got a mail for Torsten (author) with the following idea: glht(lmeglu, linfct = c("Ath1:tim2 - Ath1:tim3 = 0", ...)) He suggested to build the matrix explicitly instead

[R] Multiple comparison on lme model with 2 fixed factors

2009-08-17 Thread Billeke
Hi! I'm a bit lost while performing multiple comparisons on a lme model of that type: lmeglu=lme(glucose~Ath*tim,random=~1|Vol,na.action=na.omit,data=data) multc = glht(lmeglu, linfct = mcp(Ath = "Tukey", tim = "Tukey")) This works fine for identifying the effect of each factor. However, when I

Re: [R] Multiple comparison on lme model with 2 fixed factors

2009-08-17 Thread Dieter Menne
Billeke wrote: > > I'm a bit lost while performing multiple comparisons on a lme model of > that type: > > lmeglu=lme(glucose~Ath*tim,random=~1|Vol,na.action=na.omit,data=data) > multc = glht(lmeglu, linfct = mcp(Ath = "Tukey", tim = "Tukey")) > > This works fine for identifying the effect of

[R] multiple comparison

2008-07-31 Thread Agus Susanto
Dear all, I was trying to understand how "multcomp" package works by running the examples given in the documentation. However I still don't understand when it comes to multiple comparison set by user (please refer to "Ksub" in the code). Therefore I run 2 other cases along with the original examp

[R] multiple comparison for interaction means

2008-05-27 Thread Violeta Bartolome
Does anyone have a program for comparing interaction means (similar to HSD.test of agricolae) for a split or strip plot design? For those who are familiar with SAS I am looking for something similar to the DIFF option of the LSMEANS statement of PROC MIXED and the PDMIX800 macro. The diff option

Re: [R] multiple comparison (glht) problem

2007-11-21 Thread Chuck Cleland
Anqi Qiu wrote: > I am not sure whether there is a bug. When I tested the example given for > "glht" > in the help, I entered the following error: > > Running commands: > > amod <- aov(minutes ~ blanket, data = recovery) > rht <- glht(amod, linfct = mcp(blanket = "Dunnett"), > alte

[R] multiple comparison (glht) problem

2007-11-21 Thread Anqi Qiu
I am not sure whether there is a bug. When I tested the example given for "glht" in the help, I entered the following error: Running commands: amod <- aov(minutes ~ blanket, data = recovery) rht <- glht(amod, linfct = mcp(blanket = "Dunnett"), alternative = "less") Errors are: Err

[R] Multiple comparison tests - Homogenous subsets (i.e. for Tukey)

2007-10-23 Thread Prof. Dr. Karl-Heinz Kunzelmann
Dear all, is there any possibility to generate a table of homogeneous subsets for multiple comparison tests as in SPSS with R? I am specially interested in Tukey's B test. I have tried to find the answer myself and found an excellent description here: http://www.ppsw.rug.nl/~sda/siv/Posthoc_p