Q₁ = 10, Q₃ = 20
IQR
10.
A common rule of thumb says a value is an outlier if it is below or above .
This page is easier if you are comfortable with:
An outlier is a value that is unusually far from the rest of the data. The interquartile range (IQR) is , the spread of the middle half of the data.
Calculate the upper and lower fences and . Any value beyond a fence is flagged as an outlier.
Outliers should be investigated, not automatically removed; they may be errors or genuine extreme values. They are flagged with the interquartile range from the five-number summary, and they affect the range and the standard deviation strongly.
This page is part of Charts and diagrams in Statistics. Topics that work alongside it: Quartiles and interquartile range, Five-number summary (box plot), Range, Frequency density (histograms), Moving average and Pie chart angle.
A common rule of thumb marks a value as an outlier if it is more than 1.5 × IQR below the lower quartile or above the upper quartile.
With Q₁ = 12 and Q₃ = 20 the IQR is 8, so the upper fence is 20 + 1.5 × 8 = 32. The value 35 is above it, so it is an outlier.
These examples are worked by hand, step by step, so you can compare your own working.
For a data set, and . Is 50 an outlier?
With the same quartiles, find the lower fence.
A data set has and . Is 35 an outlier?
A few situations come up again and again. Knowing them saves time and helps you spot answers that cannot be right.
IQR
10.
lower fence Q₁ − 1.5 IQR
−5.
upper fence Q₃ + 1.5 IQR
35.
upper fence
27.
A value is a (suspected) outlier if it is below Q₁ − 1.5 IQR or above Q₃ + 1.5 IQR.
Q₃ − Q₁.
Q₁ − 1.5 × 10.
Q₃ + 15.
Q₁ = 12, Q₃ = 18.
range ✗
IQR ✓
Fence rule.
IQR only ✗
1.5 × IQR ✓
Convention.
median ✗
from the quartiles ✓
Q₁ and Q₃.
always remove ✗
investigate first ✓
Judgement.
Try each one on paper, then open the answer. Use the solver above to see the full working.
12
35
-13
55
15
12
Unlimited fresh questions with instant marking. Choose a level, work it out on paper, then type your answer.
Solve: …
Below Q₁ − 1.5 IQR or above Q₃ + 1.5 IQR.
Q₃ − Q₁.
Not automatically.
On a boxplot.
quartiles and IQR.
five-number summary.
More in Statistics and the formula sheets.