[R] Re: simple bar plot with confidence interval
Martin Henry H. Stevens
HStevens at muohio.edu
Fri Apr 26 17:17:23 CEST 2002
Looks pretty pretty to me! You might look at arrows instead of segements
and make the arrow heads 90 degrees. You should also check the mail
archives regarding this frequently requested info - try plotCI() by Ben
Bolker in archives.
At 08:02 PM 4/25/2002, you wrote:
>I camed up with the following script, which works
>except it doesn't look very pretty. If someone can
>suggest how to improve the graphics (e.g. adding a
>horizontal bar, etc.), I'd appreciate it.
>tbarHeight<-c(0.2700797, 0.7149945, 0.922099)
>names(tbarHeight)<-c("A", "B", "C")
>tl<-c(0.4256, 0.8611, 0.9883) #lower whisks
>tu<-c(0.2048, 0.5797, 0.7914) #upper whisks
>segments(x0=tbars, x1=tbars, y0=tl, y1=tu)
>--- Haun Jung <haun_jung at yahoo.com> wrote:
> > Hi, I have the following numbers as a result of
> > bootstrap:
> > Bootstrap Statistics :
> > original bias std. error
> > t1* 0.2700797 0.02168322 0.05843803
> > Intervals :
> > Level Percentile
> > 95% ( 0.2048, 0.4256 )
> > Can somebodly please show me how to plot a bar
> > with
> > confidence interval? I've searched the archive,
> > but
> > i'm a novice, so it didn't help much, and I need it
> > really urgently. I'd be immensely grateful.
> > __________________________________________________
> > Do You Yahoo!?
> > http://games.yahoo.com/
>r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
>Send "info", "help", or "[un]subscribe"
>(in the "body", not the subject !) To: r-help-request at stat.math.ethz.ch
Martin Henry H. Stevens, Assistant Professor
338 Pearson Hall
Oxford, OH 45056
Tel: (513) 529-4206
FAX: (513) 529-4243
r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !) To: r-help-request at stat.math.ethz.ch
More information about the R-help