Outlier: Difference between revisions
Jump to navigation
Jump to search
imported>Bruce M. Tindall mNo edit summary |
imported>Bruce M. Tindall (de-orphanize & copyedit) |
||
| Line 1: | Line 1: | ||
{{subpages}} | {{subpages}} | ||
In [[statistics theory|statistics]], an '''outlier''' is an observation in a data set that is so different from the other observations that it appears not to belong in the data set. | |||
The most common | The most common treatment of outliers is to exclude them from statistical calculations. | ||
The reasoning behind this is that the outliers must have been generated by a different phenomenon | The reasoning behind this is that the outliers must have been generated by a different phenomenon from the rest of the observations, for example an error in measurement, and would therefore make statistical analysis less accurate. | ||
==References== | ==References== | ||
<references/> | <references/> | ||
Latest revision as of 15:01, 25 November 2010
In statistics, an outlier is an observation in a data set that is so different from the other observations that it appears not to belong in the data set.
The most common treatment of outliers is to exclude them from statistical calculations.
The reasoning behind this is that the outliers must have been generated by a different phenomenon from the rest of the observations, for example an error in measurement, and would therefore make statistical analysis less accurate.