[R-sig-eco] pollination experiment with missing value

[hpdutra]

Hi Thierry
Thanks for the reply, you are right about lack of power. I appreciated the
suggestion of doing lmer, however I was wondering if there is book out there
explaining how to present the results of such analysis. I have Pinheiros and
Bates and Crawle's R book, and althought they do a good job explaining how
to perform these tests they don't explain how to present them on a
scientific publication.
I am more interested though in comparing some specific treatments, thus
planned contrasts are also a possiblity. Does anyone know if  reducing the
number of post hoc comparisons by using planned constrasts will increase my
power and if yes, how do I get to do these planed comparisons?
Thanks
Humberto


ONKELINX, Thierry wrote:
> 
> Dear Humberto,
> 
> I suppose you are interessed in the significance of the treatment
> factor. You can test that effect by comparing models with and without
> the term. You can get the multiple comparisons with the multcomp
> package. Here is an example using the Pastes dataset.
> 
> library(lme4)
> library(multcomp)
> data(Pastes)
> Model <- lmer(strength ~ cask + (1|batch), data = Pastes)
> Model2 <- lmer(strength ~ (1|batch), data = Pastes)
> anova(Model, Model2)
> glht(Model, linfct = mcp(cask = "Tukey"))
> confint(glht(Model, linfct = mcp(cask = "Tukey")))
> 
> PS You have a lot of treatments to test with few replicates. Testing
> less treatment with more replicates would be a better design. I'm
> affraid that the power of your current design will be rather low.
> 
> HTH,
> 
> Thierry
> 
> ------------------------------------------------------------------------
> ----
> ir. Thierry Onkelinx
> Instituut voor natuur- en bosonderzoek
> team Biometrie & Kwaliteitszorg
> Gaverstraat 4
> 9500 Geraardsbergen
> Belgium
> 
> Research Institute for Nature and Forest
> team Biometrics & Quality Assurance
> Gaverstraat 4
> 9500 Geraardsbergen
> Belgium
> 
> tel. + 32 54/436 185
> Thierry.Onkelinx at inbo.be
> www.inbo.be
> 
> To call in the statistician after the experiment is done may be no more
> than asking him to perform a post-mortem examination: he may be able to
> say what the experiment died of.
> ~ Sir Ronald Aylmer Fisher
> 
> The plural of anecdote is not data.
> ~ Roger Brinner
> 
> The combination of some data and an aching desire for an answer does not
> ensure that a reasonable answer can be extracted from a given body of
> data.
> ~ John Tukey
> 
> -----Oorspronkelijk bericht-----
> Van: r-sig-ecology-bounces at r-project.org
> [mailto:r-sig-ecology-bounces at r-project.org] Namens Humberto Dutra
> Verzonden: dinsdag 8 december 2009 0:25
> Aan: r-sig-ecology at r-project.org
> Onderwerp: [R-sig-eco] pollination experiment with missing value
> 
> Dear subscribers
> I performed a  quite simple pollination experiment: 
> 12 plants
> 12 pollination treatments per plant,
> plant 1 had treatments a, b, c,
> d... etc plant 2 had treatments a, b, c, d... 
> The idea was to run a simple anova using plants as blocks to see the
> effects of treatments on fruit production, but I lost some a few
> treatments in some plants, thus I have to deal with missing values First
> I tried the obvious, arc transformed fruits 
>> fruset.aov<-aov(arcfruit~treatment+Error(Plant),
> na.action=na.omit, fruset)
> 
> but I get the wrong DF because of the missing values, and I cannot
> perform the multiple comparisons test. Is there a better way to deal
> with this unbalanced design?
> 
> I did a little bit more research and  I decided to run a GLM for mixed
> effects using a binomial distribution
>>y<-cbind(fruits,nofruits)
>> model<-glmer(y ~ treatment+ (1|Plant), binomial,data=fruset)
> 
> but them I cannot get the anova table 
>> anova(model,test="F")
> Error in anova(model, test = "F") : 
>   single argument anova for GLMMs not yet implemented
> 
> Some people suggested using Anova function on the package car, but I
> don't see how can I get it to work with a mixed effects model like this.
> 
> 
> Any suggestions are appreciated. Are there other straight forward ways
> to analyze such data, given the missing values, and multiple comparisons
> follow up?
> Thank you
> 
> Humberto
> 
> 
> 
> 
> 
> ==========================================================
> 'Discipline - Success doesn't just happen. You have to be intentional
> about it, and that takes discipline.' - John Maxwell
> 
> 
> 
>       
> 	[[alternative HTML version deleted]]
> 
> _______________________________________________
> R-sig-ecology mailing list
> R-sig-ecology at r-project.org
> https://stat.ethz.ch/mailman/listinfo/r-sig-ecology
> 
> Druk dit bericht a.u.b. niet onnodig af.
> Please do not print this message unnecessarily.
> 
> Dit bericht en eventuele bijlagen geven enkel de visie van de schrijver
> weer 
> en binden het INBO onder geen enkel beding, zolang dit bericht niet
> bevestigd is
> door een geldig ondertekend document. The views expressed in  this message 
> and any annex are purely those of the writer and may not be regarded as
> stating 
> an official position of INBO, as long as the message is not confirmed by a
> duly 
> signed document.
> 
> _______________________________________________
> R-sig-ecology mailing list
> R-sig-ecology at r-project.org
> https://stat.ethz.ch/mailman/listinfo/r-sig-ecology
> 
> 

-- 
View this message in context: http://n2.nabble.com/pollination-experiment-with-missing-value-tp4129174p4132257.html
Sent from the r-sig-ecology mailing list archive at Nabble.com.