National EMSC Data Analysis Resource Center
The third measure of center is the mode. This one is really easy; the mode is simply the most frequent observation.
For example, let’s suppose that in a dataset of child weights, there were actually two children who were 50 pounds (and all the other weights were still just listed once). Then 50 would be the mode of our data, because 50 was the most frequent observation. Let’s also assume that in addition to those two 50 pounders, there were also three children who were 77 pounds. Now what would the mode be? Yep, it would be 77, because 77 is now the most frequent observation.
13 22 26 38 36 42
50 50 77 77 77 110
(Modified dataset of child weights.)
As you can see, this measure of center hardly requires any math at all. In the dataset of child weights we've been using (see below), there are no repeating observations at all, so we would say there is no mode.
13 22 26 36 38 42
49 50 77 81 98 110
How useful is the mode for you? Usually it is not that useful. The mode is by far the least commonly used measure of center. The times when it is most useful are when you are working with open text data or categorical data, such as multiple choice.
For instance, if I asked several people in my family where they would most like to go on vacation and the most common answer was Hawaii, I would be able to effectively say that the mode was Hawaii, and I should probably not plan my next trip to Milwaukee.
However, if I were presenting this data to others in the real world, most people would want to see the percentage breakdown of how many people said Hawaii compared with the percentages for other top locations. This is why the mode isn’t entirely useful to you; there are usually better ways of discussing data that you get from a mode. But it is still important to understand what the mode is.