The IQR Outlier Detection Rule
What you'll learn: How to use the 1.5×IQR rule to systematically flag outliers in your data by identifying values that fall outside specific boundaries around the quartiles.
The Core Concept
Now that you understand the Interquartile Range (IQR), you can apply one of the most popular outlier detection rules in statistics. The 1.5×IQR rule establishes clear boundaries beyond which data points are considered outliers:
- Lower boundary: Q1 - 1.5×IQR
- Upper boundary: Q3 + 1.5×IQR
Any value below the lower boundary or above the upper boundary is flagged as a potential outlier.
Why 1.5?
The multiplier 1.5 is a convention that John Tukey established, providing a good balance: it's strict enough to catch unusual values but lenient enough to avoid flagging too many legitimate data points. For normally distributed data, this rule typically flags about 0.7% of observations as outliers.
Think of It as a Fence
Imagine your data as houses on a street. Q1 and Q3 mark the "typical neighborhood," and IQR is the neighborhood's width. The 1.5×IQR rule builds a fence 1.5 times that width beyond each edge. Anything outside that fence doesn't belong to the normal neighborhood.
When to Use It
This rule works well when:
- Your data has a reasonably symmetric distribution
- You want a quick, interpretable method
- You're exploring data and need a starting point for outlier investigation
Unlike Z-score methods, the IQR rule is resistant to outliers themselves—since it uses quartiles (robust statistics) rather than the mean and standard deviation.
Key Takeaway: The 1.5×IQR rule flags outliers as values below Q1 - 1.5×IQR or above Q3 + 1.5×IQR, providing a robust, distribution-independent method for anomaly detection.