Outlier Calculator

What the outlier calculator does

An outlier is a value that sits far enough from the rest of the data to be worth a second look. This calculator finds them using the standard quartile method, and shows the working: the first and third quartiles, the interquartile range, and the two fences that mark where the normal data ends and the outliers begin.

Spotting outliers early matters, because a single stray value can quietly distort a mean, a standard deviation, or a chart. Below is how the calculator decides what counts as one.

How to use it

1. Enter your numbers in the box, separated by commas, spaces, or new lines.
2. Press Calculate for the outliers, the quartiles, the interquartile range, and the fences, or Reset to clear it.

How the outliers are found

The calculator uses the interquartile range, the spread of the middle half of the data. It sorts your numbers, finds the first quartile and the third quartile, and takes the distance between them as the interquartile range. Then it builds a fence a set distance beyond each quartile, and anything outside those fences is flagged as an outlier.

Lower fence = Q1 minus 1.5 times IQR    Upper fence = Q3 plus 1.5 times IQR

Any value below the lower fence or above the upper fence is an outlier. Everything between them is treated as ordinary data.

The 1.5 times IQR rule

The multiplier of 1.5 is the convention introduced by the statistician John Tukey, and it is the one most textbooks and box plots use. It is a sensible middle ground: wide enough that ordinary variation is not mistaken for an outlier, but tight enough to catch the values that really do stand apart.

Some analyses use a second, wider fence at 3 times the interquartile range to separate the merely unusual from the truly extreme, sometimes called far-out values. This calculator uses the standard 1.5 rule, which is the right default for flagging outliers in most work.

A worked example

Take the ten numbers 10, 12, 13, 14, 15, 16, 17, 18, 19, 95. The first quartile is 13 and the third is 18, so the interquartile range is 18 minus 13 = 5.

The fences sit 1.5 times that range beyond each quartile: the lower fence is 13 minus 7.5 = 5.5, and the upper fence is 18 plus 7.5 = 25.5. Every value falls inside those fences except the 95, which sails past the upper fence and is flagged as the single outlier. The eye already suspected it, and the rule confirms it.

What to do with an outlier

Finding an outlier is the start of a question, not the end of one. Sometimes it is a mistake, a typo or a bad reading, and once confirmed it can be corrected or removed. Other times it is entirely real and the most interesting number in the set, the unusually large sale or the one patient who responded differently.

So the honest move is to investigate rather than delete on sight. An outlier flagged here is a value asking why it is different, and the answer decides whether it stays, goes, or becomes the thing you actually study.

Entering your data, and the method

You can separate your numbers with commas, spaces, or new lines, in any mix, and the calculator sorts them for you. It finds the quartiles with the exclusive method, the same one used by our quartile calculator, so the fences here line up with the quartiles reported there. For data with an odd number of values, remember that quartile methods vary between tools, which can shift the fences a little.

Questions people ask

What is an outlier?

A value that lies far from the rest of the data, beyond a fence set at 1.5 times the interquartile range past the first or third quartile.

How does the calculator decide what is an outlier?

It builds a lower fence at Q1 minus 1.5 times the IQR and an upper fence at Q3 plus 1.5 times the IQR. Any value outside those fences is flagged.

Why 1.5 times the interquartile range?

It is the standard convention from John Tukey, balanced to catch genuine outliers without flagging ordinary variation. A wider fence of 3 times the IQR marks extreme values.

Should I remove outliers?

Not automatically. Investigate first. An outlier can be an error to fix or a real, important value. Let the reason for it decide, rather than deleting on sight.

References

A quick note on where the methods here come from. The interquartile range and the 1.5 times IQR rule for outliers are set out in the NIST/SEMATECH e-Handbook of Statistical Methods, the US government's public statistics reference. OpenStax Introductory Statistics is a free, widely used textbook that covers outliers and the fence rule.

1. NIST/SEMATECH e-Handbook of Statistical Methods (interquartile range and outliers). https://www.itl.nist.gov/div898/handbook/
2. OpenStax, Introductory Statistics (outliers and the interquartile range). https://openstax.org/details/books/introductory-statistics-2e