Outlier Calculator
Test cases replayed : 2 of 2 match · Methodology · No outside source listed
Paste or type a list of numbers to flag the values that fall outside Tukey's fences.
Result
Outliers
First quartile (Q1)
- Third quartile (Q3)
- Interquartile range (IQR)
- Five-number summary (min, Q1, median, Q3, max)
- Count
Estimate for planning only, not tax, legal, financial or medical advice. This calculator uses the method explained on this page.
This browser did not allow copying. The sentence is in the box below, already selected: copy it with your keyboard or the menu.
How to use this calculator
Fill in the fields in this order; each step takes you to its field.
- Numbers (separated by commas, spaces or new lines): type or paste your values.
- Read the result: Outliers; the panel also shows First quartile (Q1), Third quartile (Q3), Interquartile range (IQR), Five-number summary (min, Q1, median, Q3, max) and Count.
Data plot
Table of values
| Value | Count |
|---|
How this calculator works
Tukey's rule (Exploratory Data Analysis, 1977): a value is an outlier if it lies below Q1 − 1.5 × IQR or above Q3 + 1.5 × IQR, where IQR = Q3 − Q1.
Quartiles are the medians of the lower and upper halves of the sorted list, the median excluded when the count is odd (TI-83/84 method). Values beyond 3 × IQR from the quartiles are sometimes called extreme outliers.
An outlier is a value worth checking, not necessarily an error: it may be a typing mistake or a real, unusual observation.
Worked example
| Numbers (separated by commas, spaces or new lines) | 3, 21, 22, 24, 25, 26, 27, 28, 29, 31, 62 |
|---|
| Outliers | 3, 62 |
|---|---|
| First quartile (Q1) | 22 |
| Third quartile (Q3) | 29 |
| Interquartile range (IQR) | 7 |
| Five-number summary (min, Q1, median, Q3, max) | 3, 22, 26, 29, 62 |
| Count | 11 |
Frequently asked questions
Which values are outliers in 3, 21, 22, 24, 25, 26, 27, 28, 29, 31, 62?
Q1 = 22, Q3 = 29 and IQR = 7, so the fences are 11.5 and 39.5: 3 and 62 are outliers.
Should I delete outliers?
Only if you can show they are errors. Otherwise report them, or use measures such as the median and IQR that they barely affect.