Cody’s Data Cleaning Techniques Using SAS® Software

Checking a Range Based on the Interquartile Range

Yet another way to look for outliers is a method devised by advocates of exploratory data analysis (EDA). This is a robust method, much like the previous method described, based on a trimmed mean. It uses the interquartile range (the distance from the 25^th percentile to the 75^th percentile) and defines an outlier as a multiple of the interquartile range above or below the upper or lower hinge, respectively. For those not familiar with EDA terminology, the lower hinge is the value corresponding to the 25^th percentile (the value below which 25% of the data values lie). The upper hinge is the value corresponding to the 75% percentile. For example, you may want to examine any data values more than ...