Pie Chart
Pie charts along with bar graphs are the most common types of
graphical representation for qualitative data. It
takes categorical data and breaks it down by group, showing the percentage of data points that fall into each
group. Since a pie chart takes on a shape of a circle, the slices that represent each group can easily be
compared and contrasted. Each data point in a pie chart must fall into one and only one category, and the sum of
all slices should be
100% or close to it, subject to a bit of rounding error. Pie chart does not have to say how much each slice is,
only what percentage it is of the total, although absolute
values of slices and/or total are sometimes included as
The following tips help to evaluate a pie chart for statistical
- Checking that the percentages of all slices add up to 100% or very close to it- any round-off error should be very small.
- The "Other" slice of the pie chart should not be larger than many other slices.
- The total number of units should be reported with the pie chart.
- Three-dimensional pie charts should be avoided. They don't show the slices in their proper proportions- the slices in front look larger than they should be.
Ideally, a pie chart should not have too many slices, because a large number of slices distracts the
reader from
the main point(s) the pie chart is trying to relay. However, lumping many small remaining categories into one
slice of
"Other" that together is one of the largest in the whole pie chart, leaves the readers wondering what's included
in that particular
Unlike a bar graph, with a pie chart the scale cannot be
changed to over-emphasize or downplay the
results. No
matter how a pie chart is sliced up it is always a sliced up circle, and making the pie chart bigger or smaller
does not change the relative proportions of the