Variability
Variability is the tendency of values to differ, both among the observations in one data set and from one sample to the next.
Variability is the reason statistics exists, since identical values would leave nothing to summarize and nothing to infer. Inside a single data set you measure it with the standard deviation or the IQR, which is how two classes can both average 75 while one runs from 70 to 80 and the other from 45 to 100. Across repeated samples it appears as sampling variability, the sample-to-sample bounce in a statistic such as (x-bar), and that bounce shrinks as the sample size grows. Standard error is the name for the size of that second kind of variability.
Where this comes up
- How to compare two distributionsGuide
- Comparing two distributions practice problemsPractice
- Does a bigger sample fix bias? Why size failsGuide
- How to describe a distribution (and get full credit)Guide
- What is a cluster sample? (with examples)Guide
- Identifying bias practice problems (8 solved)Practice
- How to choose a sampling methodGuide
- Simple random vs stratified vs cluster samplingGuide
18 pages on the site use this term.
More describing data terms, or browse the full statistics glossary.