The median of a set of numbers is equivalent to the “middle” number in a list of observations when values are ordered from least to greatest or greatest to least. If the list contains an even number of observations, then the median is the arithmetic mean of the two middle items. In this case, the median may be a value that does not appear in the original list.

Like the mean, the median can be a useful measure against which to judge the relative uniqueness of a given data point. However, it is especially important in a data set that is skewed; in other words, in a data set where one or more outliers is present. One way to judge whether or not this is the case is by comparing the mean and the median of a given data set. If the two values are relatively close, the mean may be a more accurate measure of central tendency. If they diverge significantly, the median is likely the more reliable indicator.