On 2010-06-04 0:14, Thomas von Känel wrote:
hi,
i'm using /"boxplot()"/ to show some data:

x<- c(0.99, 0.97, 0.91, 0.72, 1.00, 0.99, 1.02, 0.90, 0.91, 0.90, 1.02,
0.90, 1.35, 1.01, 0.92)
boxplot(x)

is it correct when i say: /"Boxes represent interquartile ranges (IQRs);
bold horizontal lines, medians; whiskers, lowest and highest values
still within 1.5 x IQR; open circles, outliers."?


That's essentially correct, except that quartiles can be
defined in more than one way; see ?quantile and the
discussion leading to comments in
https://stat.ethz.ch/pipermail/r-help/2010-May/239074.html.

Note that the box limits are the 'hinges' given by
fivenum(x) and their difference need not equal IQR(x) which
uses quantile(..., type=7). [For your data above, they do
happen to coincide.]

 -Peter Ehlers

/thanks in advance for any help!
cheers, tom
human genetics, bern/
/


______________________________________________
R-help@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.

Reply via email to