[R] mild and extreme outliers in boxplot
ottorino-luca.pantani at unifi.it
Thu Aug 20 09:25:01 CEST 2009
I'm very sorry for all this, but still serene.
I'm (trying) to use R since may be 5 or 6 years now.
What I learned from this list is that you have to show some code to let
others to help you out, a thing that Rnewbye did not in this particular
I had a look myself at the help pages and see that "something" was there
that could help Rnewbye.
> outlty, outlwd, outpch, outcex, outcol, outbg: outlier line
> type, line width, point character, point size expansion,
> color, and background color. The default 'outlty=
> "blank"' suppresses the lines and 'outpch=NA' suppresses
My answer was somehow provocative, but I was ready to help, not to
patronize (as many times I saw on this list).
I tried myself to change the appearance of the circles and other aspect
of the plot, uncorrectly assuming that it could be extended to the
problem of Rnewbye.
I surely made a mistake, and I apologize for this. This is is my only fault.
BUT PLEASE do not forget that if Rnewbye answered to my post (with a
piece of code for example) I would have helped him. As I was always
helped, harshly or not.
> This is the sort of response that gives R-help a bad name.
I did not know that R-help had a bad name.
I myself received sometimes some harsh answers, but never lamented about.
Gabor Grothendieck ha scritto:
> I agree its not completely obvious from that answer but that
> does not mean the responder deserves to be attacked.
> The circle part is actually the default and albeit with difficulty
> the help files do give the info we need to produce this:
> bp <- boxplot(c(1:50, 80, 100, 200), outpch = NA)
> with(bp, points(group, out, pch = c(1, 1, 8)))
> which can be suitably generalized for other situations.
> On Wed, Aug 19, 2009 at 8:31 PM, Rolf Turner<r.turner at auckland.ac.nz> wrote:
>> I despair. ..........
Ottorino-Luca Pantani, Università di Firenze
Dip. Scienza del Suolo e Nutrizione della Pianta
P.zle Cascine 28 50144 Firenze Italia
Tel 39 055 3288 202 (348 lab) Fax 39 055 333 273
OLPantani at unifi.it http://www4.unifi.it/dssnp/
More information about the R-help