The pie chart.
A pie chart is a circle whorepresents the total of the data and to each category is assigned an area directly proportional to its frequency.
Pies, how good they are! The problem is that, as you know, what is not frowned upon is fattening or causes cancer. And pies could not be the exception, so be careful to avoid eating too much so that they don’t end in your spare tyre or in worse places.
But there is a type of pie that is not fattening at all (nor causes cancer), and this is the pie chart, which is frequently used in statistics. Did I say just frequently? I am probably short. Because it is not fattening nor has detrimental health effects there is a tendency to abuse their use.
The pie chart
The pie chart, or circle chart, is easy to draw. It consists of a circle whose area represents the total of data. Thus, an area proportional to its frequency is assigned to each category so the much frequent categories have larger areas and you can get an idea of how frequencies are distributed among categories at a glance.
There are three ways to calculate the area of each sector. The simplest is to multiply the relative frequency of each category by 360 °, obtaining the degrees corresponding to each sector.
The second is using the absolute frequency of the category, according to the following rule of thirds:
Finally, the third way is to use the proportions or percentages of the categories:
These formulas are very simple but, anyway, there will be no need for them because the program we use to draw the graph will do it for us.
The pie chart is designed to represent nominal categorical variables, although it is not uncommon to see pies representing other variables. However, in my humble opinion, this is not entirely correct.
For example, if we make a pie chart for an ordinal qualitative variable we will lose the information on the hierarchy of variables, and it would be more correct to use a graphic that allows sort categories from less to more. And this figure is none other than the bar chart.
The pie chart is especially useful when there are few variables. If you have many variables interpretation ceases to be so intuitive, although we can always complete the chart with a frequency table to help us better interpret the data. Another tip is to be very careful with 3D effects when drawing the pie: too artistic pies could be difficult to understand.
We’re leaving…
Finally, just say that it makes no sense to use a pie to represent a quantitative variable. For that there is another more appropriate procedure, which is to use a histogram that best represents the frequency distribution of a continuous quantitative variable. But that is another story…