Skip to content

plot.design and NAs

2 messages · Steven Sullivan, Uwe Ligges

#
Hello all--

I'm trying to quickly, graphically, summarize the differences in the sample
proportion of "yes" responses in a 0-1 variable across sites.

I'm looking for a quick way to do one of the following:

(1) add means onto boxplots (I know there's a boxmeans=T toggle in plot(.),
but can I do this on proper boxplots?)
(2) run plot.design on data containing NAs?  (I have tried fun = function(x)
mean(x, na.rm=T) in plot.design(.)).

Best,
STS




-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
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
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._
#
Steven Sullivan wrote:
Is it? I cannot find it.
A quick hack would be something like

 a <- rnorm(10)
 b <- rnorm(10)
 boxplot(a, b)
 segments(1:2 - 0.4, mm <- c(mean(a), mean(b)), 
     1:2 + 0.4, mm, col = "red")

(with the default boxwidth of 0.8 and the placement of the middle of
boxes at 1, 2, ... )

A cleaner solution would be to change the R code of bxp().
Well, I cannot find plot.design anywhere; in which package is it
included?


Uwe Ligges
-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
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
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._