Hi Rosa,
Your data never seem to get through. Nevertheless, here is a suggestion:
rodat<-data.frame(id=1:20,age=sample(c("10-20","21-30","31-40"),20,TRUE),
weight=c(sample(40:70,18),110,120))
robp<-boxplot(weight~age,rodat)
rodat$id[which(rodat$weight %in% robp$out)]
Jim
On Mon, Sep 5, 2016 at 9:38 PM, Rosa Oliveira <rosit...@gmail.com> wrote:
> Dear all,
>
> I have searched all over and didn´t found an answer :(
>
> I need urgently to "extract" de identification of the weight outliers of
> the participants of a study.
>
> So, I have a data base with several variables:
> id
> weight
> are 2 off them.
>
> So, I've done a boxplot and found the weight have outliers. Now I need to
> identify the id's of those participants.
> I can get the outliers values, nonetheless lots os them are not correct for
> some vriables.
>
> Can you please help me?
>
> boxplot(WEIGHT~AGE,baseR,range=3) #print WEIGHT boxplot
> boxplot(WEIGHT~AGE==1,,baseR,range=3, plot=FALSE)$out # find outliers
> values to age 1 (example)
>
>
> I attach the data.
>
> Best,
> Rosa Oliveira
>
> __________________________________
>
> Antes de imprimir este e-mail pense bem se tem mesmo que o fazer.
> Há cada vez menos árvores.
> Não imprima, pense na sua responsabilidade e compromisso com o MEIO
> AMBIENTE!
> <http://pt.dreamstime.com/cora-ccedil-atildeo-criado-das-folhas-de-aacutervores-diferentes-thumb12275776.jpg>
> <http://pt.dreamstime.com/cora-ccedil-atildeo-criado-das-folhas-de-aacutervores-diferentes-thumb12275776.jpg>
> ______________________________________________
> R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see
> 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.
______________________________________________
R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see
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.
