When we measure anything, the measurements will form a range from low to high. That’s true of everything from temperatures to cost-per-thousand (CPM) measures in advertising. The center of that range is the average. Most scores will tend to bunch up around the average – and that is what a central tendency is – the tendency for data points to cluster around the centerpoint of the measurement range.
When you think about it, one of the main reasons we do stats is to understand why some things are different from others, or different from the average. Why did this program perform better than average? Why did this ad get more clicks than the others?
The three most common measures of central tendency are mean, median, and mode. These three are all measures of central tendency and are all referred to as averages. In normal life, we usually say ‘mean’ when we refer to an average, but not always.
Mean
The mean is the total sum of all values in a set divided by the number of values in that set. It gives us an average value and is useful for understanding the overall performance or tendency of data. The mean can be strongly impacted by extreme values, or what we call outliers – measures that are much higher or lower than the majority of scores.
Median
The median is the middle value of a range of measures. If there’s an even number of observations, the median is the average of the two middle numbers. It’s particularly useful for understanding the center of a data set, especially when the data have extreme values (outliers). If there are 11 measures in a data set, the 6th measure from the top and the bottom is the median, leaving 5 measures above and below it. If there were 10, the median would be the average of the 5th and 6th value.
Mode
The mode is the value that appears most often in a data set, and is useful for identifying common or popular choices within a dataset. There can be more than one mode if multiple values appear with the same highest frequency (multimodal).
