6. Percentiles and Quartiles
6.2 Finding Outliers Using Quartiles
We can use quartiles to identify outliers or data points that are wildly discrepant with the rest of the data. For this application, we need another definition of data dispersion :
With the IQR any data value that satisfies:
(a) less than
(b) greater than
…is considered an outlier. This is one of many ways one can define an outlier. As we will discuss below, it is a robust way of identifying outliers.
Example 6.4 : Consider the data of Example 6.2. We found
Following our rules for finding outliers, we compute:
(a) lower acceptable value limit
(b) upper acceptable value limit
and 50 > 36.5 so 50 is considered an outlier.