skewed distribution

Last reviewed 01/2018

A skewed distribution describes a population whose values are not equally distributed about the mean.

In a positive skew there are a small number of very large values; this means that when the curve is drawn there is a long tail after the peak. Put statistically, the mode is lowest, then the median, then the mean is highest, effectively dragged upwards by the few high results.

In a negative skew the reverse occurs; there are a small number of small values. The tail appears before the peak, and the mean is the smallest, followed by the median and the mode.