[R] "continuous" boxplot?

[roger koenker]

If what is desired is a plot of conditional quantiles of y given x,
then loess plots of y on x binned on y is really not a good strategy.

You might try something like this:

  library(quantreg)

x <- (0:1000/1000)*2*pi
y <- sin(2*x) + rnorm(1001)/5
plot(x,y,pch =".")

plot(rqss(y ~ qss(x)),col="red")
plot(rqss(y ~ qss(x),tau=.1),col="red")
plot(rqss(y ~ qss(x),tau=.9),col="red")

url:    www.econ.uiuc.edu/~roger            Roger Koenker
email    rkoenker at uiuc.edu            Department of Economics
vox:     217-333-4558                University of Illinois
fax:       217-244-6678                Champaign, IL 61820


On Oct 2, 2007, at 1:57 PM, Bert Gunter wrote:

>
>
> Folks:
>
> I found the references in the previous replies to this vexing data
> visualization issue to be quite interesting and useful. I think it  
> fair to
> say that there is no single "best" way to do this -- it all depends  
> on what
> you need to learn , and probably several alternative displays will be
> necessary to get the important information the data have to convey.
> However,as always, this issue has been considered before, and it  
> may be
> worthwhile to at least consider an already available "standard"  
> approach"
> using shingles and a trellis-type plot. ?xyplot and ?shingle should  
> get you
> started (you probably want to shingle or bin on quantiles of y). The
> canonical reference is Bill Cleveland's VISUALIZING DATA (see  
> "coplots").
>
>
> Bert Gunter
> Genentech Nonclinical Statistics
>
>
> -----Original Message-----
> From: r-help-bounces at r-project.org [mailto:r-help-bounces at r- 
> project.org] On
> Behalf Of Jim Porzak
> Sent: Tuesday, October 02, 2007 11:19 AM
> To: Karin Lagesen
> Cc: r-help at r-project.org
> Subject: Re: [R] "continuous" boxplot?
>
> Karin,
>
> I like to use bagplots in these cases where there are a lot of  
> cases and
> scatter plots become one big smudge.
>
> See
> http://www.wiwi.uni-bielefeld.de/~wolf/software/R-wtools/bagplot/ 
> bagplot.pdf
>
> And some further examples on slides 36 - 39 of
> http://www.porzak.com/JimArchive/ 
> JimPorzak_CIwithR_useR2006_tutorial.pdf
>
> -- 
> HTH,
> Jim Porzak
> Responsys, Inc.
> San Francisco, CA
> http://www.linkedin.com/in/jimporzak
>
> On 10/1/07, Karin Lagesen <karin.lagesen at medisin.uio.no> wrote:
>>
>>
>>
>> I have two vectors x and y, which I would like to plot against each
>> other. I am also displaying other data in this plot. However, I have
>> about 1 million points to plot, and just plotting them x againt y is
>> not very informative. What I'd like to do is to do sort of a
>> continuous box plot.
>>
>> My x values goes from -1 to 1 and my y values from 0 to 1, so I4d  
>> like
>> to plot the median and quantiles, and possibly also all of the
>> outliers somehow. Are there any facilities in R for doing something
>> like this, or would I need to do this the hard coded way?
>>
>> Thankyou very much for your help!
>>
>> Karin
>> --
>> Karin Lagesen, PhD student
>> karin.lagesen at medisin.uio.no
>> http://folk.uio.no/karinlag
>>
>> ______________________________________________
>> R-help at r-project.org mailing list
>> 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.
>>
>
> 	[[alternative HTML version deleted]]
>
> ______________________________________________
> R-help at r-project.org mailing list
> 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.