Re: [S] Pie diagrams anyone?

Z. Todd Taylor (Todd.Taylor@pnl.gov)
Fri, 13 Nov 1998 08:02:16 -0800


Bill Venables <wvenable@attunga.stats.adelaide.edu.au> wrote:

> The answer is yes, I do rather look down upon pie diagrams as an
> ineffective device and something that can be easily bettered, but
> also as something so typical of the abuses of statistics that
> Disraeli so justifiably ridiculed. Nevertheless I am curious to
> know what other people think about them. Am I alone in this?

I'm not a statistician but do create a lot of visual presentations
of data. I don't think pie charts should be banned but also can't
think of a case where some other display wouldn't work better.

Their major weaknesses from my point of view:

* Mentally assessing proportions from differences in angular
slabs is not as easy as from linear slabs. People who look
at pie charts almost always ask "what are the actual
percentages?" A table would do almost as well.

* Other presentations (e.g., bar charts, dot plots) can show
not only proportions, but magnitude as well.

* Small pie slices are next to impossible to mentally assess.

* More than three or four pie slices are next to impossible to
mentally assess.

* Mentally comparing two pie charts is not as easy as comparing
two bar or dot charts. The latter create "shapes" that the
mind can retain and contrast. The former have all exactly
the same shape.

Their major advantage, of course, is that managers and most
clients think they like them.

--Todd

-- 
Z. Todd Taylor
Pacific Northwest National Laboratory
Todd.Taylor@pnl.gov
Why are they called 'long shorts'?
-----------------------------------------------------------------------
This message was distributed by s-news@wubios.wustl.edu.  To unsubscribe
send e-mail to s-news-request@wubios.wustl.edu with the BODY of the
message:  unsubscribe s-news