An outlier is simply a score in a distribution of scores that is far away from the other scores in magnitude. If we were to establish a frequency distribution of household income, then the score for Bill Gates would be an outlier because Mr. Gates has a shockingly large income compared to the average person. Outliers are commonly defined as scores that fall more than three standard deviation units either side of the mean (we will discuss standard deviation in a later section).
Outliers and Skew
A distribution is said to be skewed if it has outliers at one end and not the other. That is, scores tend to “lean” toward one side of the distribution. When the outliers are on the right, the distribution is said to have a positive skew. When the outliers are on the left, the distribution is said to have a negative skew.
[ Back | Contents | Next ]
Last Modified: 06/29/2018