Yes, the range includes outliers. The range is simply the largest value in a dataset minus the smallest value, and it makes no distinction between “normal” data points and extreme ones. If an outlier happens to be your highest or lowest value, it gets used in the calculation, and it can dramatically inflate the result.
How Range Is Calculated
The range uses the absolute maximum and minimum values in your dataset, no matter how extreme they are. There’s no built-in filter or adjustment. If you have test scores of 72, 78, 80, 85, 88, and 91, the range is 91 minus 72, which equals 19. Straightforward.
Now add one outlier. Say a student scored 12 on that same test. The range jumps from 19 to 79 (91 minus 12). That single data point nearly quadrupled the range, even though the other six scores barely changed. This is exactly why statisticians call the range a “non-robust” measure of spread: it only looks at two data points (the extremes), so one unusual value can distort the entire picture.
A Real Example of Outlier Distortion
Consider quarterly home sales for 10 realtors: 2, 2, 3, 4, 5, 5, 6, 6, 7, and 50. That last number is a clear outlier. With it included, the range is 48 (50 minus 2). Remove it, and the range drops to just 5 (7 minus 2). The standard deviation tells a similar story, jumping from 1.81 without the outlier to 14.51 with it. Meanwhile, the median barely moves (stays at 5.00 either way), and the interquartile range shifts only from 3.50 to 3.00. The range and standard deviation are highly sensitive to outliers. The median and interquartile range are not.
Why the Interquartile Range Resists Outliers
If range is so easily thrown off, what should you use instead? The interquartile range (IQR) is the most common alternative. It measures the spread of only the middle 50% of your data by subtracting the 25th percentile (Q1) from the 75th percentile (Q3). Because it ignores the tails entirely, extreme values at either end have no effect on it.
The IQR is also the basis for identifying outliers in the first place. The standard method, sometimes called Tukey’s fences, works like this: multiply the IQR by 1.5, then subtract that number from Q1 to get a lower fence and add it to Q3 to get an upper fence. Any data point outside those fences is flagged as an outlier. For example, if Q1 is 80 and Q3 is 90, the IQR is 10, and 1.5 times that is 15. The lower fence is 65, the upper fence is 105, and any score below 65 or above 105 would be considered an outlier.
How Box Plots Handle This Visually
Box plots (also called box-and-whisker plots) offer a helpful visual distinction. The box itself spans from Q1 to Q3, representing the middle 50% of data. The whiskers extend to the most extreme data points that are not outliers. Any values beyond the whiskers are plotted as individual dots. So when you look at a box plot, you can immediately see the “normal” range of the data and any outliers separated out. The CDC’s data visualization guidelines use the same 1.5 times IQR rule to draw the boundary between whisker and outlier.
This visual separation is one reason box plots are so popular for exploratory analysis. The full range (including outliers) is still visible on the chart, but the structure of the plot makes it obvious which points are driving that range and which represent the bulk of the data.
When to Use Range vs. IQR
The range is fine when your data is clean and you need a quick, intuitive sense of total spread. It’s easy to calculate and easy to explain. But the moment your dataset contains even one extreme value, the range becomes misleading. It will suggest your data is far more spread out than it actually is for the vast majority of observations.
Use the IQR when you want a measure of spread that reflects where most of your data actually lives. It’s especially valuable when you suspect outliers, when your data is skewed, or when you’re comparing variability across groups that might have different numbers of extreme values. The mean, range, variance, and standard deviation are all sensitive to outliers. The median and IQR are resistant to them.
If you’re working in a spreadsheet and need a practical approach, calculate both. The gap between the range and the IQR can itself be informative: a range of 48 alongside an IQR of 3 (as in the realtor example) immediately tells you that extreme values are stretching your data far beyond where most observations fall.