From: Marc Schwartz <MSchwartz_at_mn.rr.com>

Date: Sat 02 Jul 2005 - 23:32:04 EST

R-help@stat.math.ethz.ch mailing list

https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html Received on Sat Jul 02 23:34:54 2005

Date: Sat 02 Jul 2005 - 23:32:04 EST

On Sat, 2005-07-02 at 06:09 -0700, Nick Drew wrote:

> I did not find an answer to my question after a quick

*> search using the R
**> search engine so thought I'd ask away:
**>
**> Does any know if there's a function exists to create
**> an interrupted Y axis?
**> What I mean by interrupted Y axis is that part of the
**> Y axis has been
**> removed or excised to permit one to see parts of the
**> data in more detail.
**>
**> Perhaps an example will make this clear. Please go to
**> http://www.jbc.org/cgi/reprint/274/41/28950 and open
**> the PDF document
**> located there. Go to page 4, figure 2c provides a
**> crude example of what I
**> mean by interrupted Y axis. Part of the Y axis between
**> 800 and 4500 has been
**> removed to permit easy inspection of the upper end of
**> the range of data.
**> (This is not my work but simply an example of what I'm
**> trying to describe.)
**> One finds these interrupted Y axis graphs in
**> newspapers or other
**> periodicals, more often than not as a bar chart.
**>
**> Does a function in R exist to permit on to this easily
**> to a graph? If not,
**> would such a function be useful? If yes, would the
**> grid package be the right
**> tool for me to try and implement this?
**> ~Nick
*

Using:

RSiteSearch("axis break")

comes up with 78 hits. You might want to consider some of the approaches
taken, including the axis.break() function in the 'plotrix' package on
**CRAN.
**
Note however that the examples (ie. newspapers) you site are called "Pop
Charts" by Bill Cleveland in his book The Elements of Graphing Data and
are highly criticized.

If you have such disparate ranges you might want to consider separate plots and/or log scaling. Be careful however, that expanding the vertical axis to isolate specific data can result in the visual perception of significant difference where none exists. This notion is also explored by Cleveland and Tufte ("The Visual Display of Quantitative Information").

**HTH,
**
Marc Schwartz

R-help@stat.math.ethz.ch mailing list

https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html Received on Sat Jul 02 23:34:54 2005

*
This archive was generated by hypermail 2.1.8
: Fri 03 Mar 2006 - 03:33:11 EST
*