Resistant vs. Nonresistant Measures

Overview

Some measures of center and spread are more easily influenced by outliers and/or skewness than others. We differentiate between those which are easily influenced from those which are not by sorting them as 'nonresistant' and 'resistant.' 

Nonresistant measures are affected by outliers/skewness, and hence are better for symmetric data.

Resistant measures are not affected as much, and hence can be used for data that has outliers or is skewed. 

Visual Example

The following animation demonstrates the relationship between mean and median as distributions become more skewed.