Setting the whisker range for box plots

I would like to have the extreme end of the upper whisker
on the box plot co-incide with the 98% of the data.

According to the documents:
whis (default 1.5) defines the length of the whiskers as
a function of the inner quartile range. They extend to the
most extreme data point within ( whis*(75%-25%) ) data range.

So, in theory, a value of whis=1.9 should be what is needed
but this seems to produce a much lower point - what value
do I need to use?

Thanks
Derek

···

--
This message is subject to the CSIR's copyright, terms and conditions and
e-mail legal notice. Views expressed herein do not necessarily represent the
views of the CSIR.

CSIR E-mail Legal Notice
http://mail.csir.co.za/CSIR_eMail_Legal_Notice.html

CSIR Copyright, Terms and Conditions
http://mail.csir.co.za/CSIR_Copyright.html

For electronic copies of the CSIR Copyright, Terms and Conditions and the CSIR
Legal Notice send a blank message with REQUEST LEGAL in the subject line to
CallCentre@...1230...

This message has been scanned for viruses and dangerous content by MailScanner,
and is believed to be clean.

I'd be happy to be shown wrong, but it seems the current
incarnation of boxplot cannot do this.

The current syntax is:

boxplot(x, notch=0, sym='+', vert=1, whis=1.5,
        positions=None, widths=None)

What it *could* have to support what is needed is
an extra parameter:

boxplot(x, notch=0, sym='+', vert=1, whis=1.5,
        positions=None, widths=None, percentile=False)

When percentile=True, then the program would treat
the value of whis as a percentile value (0.001 to 100) and
plot the whiskers and outliers accordingly.

For reference, please see:

and the section that says:
"There are alternative implementations of this detail of the
box plot in various software packages, such as the whiskers
extending to at most the 5th and 95th (or some more extreme)
percentiles"

and for examples of such an implementation:
http://www.originlab.com/index.aspx?s=8&lm=214&pid=959
or
http://ploticus.sourceforge.net/doc/rangebar.html
(see the option called "tailmode" which allows switching
between 5th and 95th percentile, min and max, or 1.5 x IQR.)

Thanks
Derek

"Derek Hohls" <DHohls@...1229...> 2007/01/23 03:29 PM >>>

I would like to have the extreme end of the upper whisker
on the box plot co-incide with the 98% of the data.

According to the documents:
whis (default 1.5) defines the length of the whiskers as
a function of the inner quartile range. They extend to the
most extreme data point within ( whis*(75%-25%) ) data range.

So, in theory, a value of whis=1.9 should be what is needed
but this seems to produce a much lower point - what value
do I need to use?

Thanks
Derek

···

--
This message is subject to the CSIR's copyright, terms and conditions and
e-mail legal notice. Views expressed herein do not necessarily represent the
views of the CSIR.

CSIR E-mail Legal Notice
http://mail.csir.co.za/CSIR_eMail_Legal_Notice.html

CSIR Copyright, Terms and Conditions
http://mail.csir.co.za/CSIR_Copyright.html

For electronic copies of the CSIR Copyright, Terms and Conditions and the CSIR
Legal Notice send a blank message with REQUEST LEGAL in the subject line to
CallCentre@...1230...

This message has been scanned for viruses and dangerous content by MailScanner,
and is believed to be clean.