In a dataset, a value that falls notably farther from the center than almost all of the other values is called an outlier. Whether a particular value should be considered an outlier depends on the distribution and sample size. In general, except in very large samples, one would be likely to treat any value that falls more than three standard deviations from the mean as an outlier.

Outliers have no effect on the median or mode, but can significantly distort the mean. A commonly cited example is that if a group of math teachers is joined by a billionaire, then each of them becomes wealthy—on average.

Outliers can be caused by variability in the individuals being measured, or by measurement error. If measurement error is suspected, the outlier might best be removed from the dataset before it is analyzed further or any conclusions drawn.

Citation Info

  • [MLA] “outlier.” Platonic Realms Interactive Mathematics Encyclopedia. Platonic Realms, 21 Feb 2014. Web. 21 Feb 2014. <>
  • [APA] outlier (21 Feb 2014). Retrieved 21 Feb 2014 from the Platonic Realms Interactive Mathematics Encyclopedia:


Get the ultimate math study-guide Math & Me: Embracing Successproduct thumbnail image Available in the Math Store
detail from Escher pic Belvedere

Are you a mathematical artist?

Platonic Realms is preparing an online gallery space to showcase and market the works of painters, sculptors, and other artists working in a tangible medium.

If your work celebrates mathematical themes we want to hear from you!

Please let us know about yourself using the contact page.