The number of people (or things) in a sample. Increasing the sample size typically reduces the variability of any form of average or similar measure and is one of the ways to increase statistical power. However, you typically have to increase the sample size a lot – for example to reduce the standard deviation (s.d., σ) by 10 you need a sample size 100 times larger. The noise–effect–number triangle suggests other factors that can be manipulated to increase statistical power.

Used on pages 24, 30, 36, 50

Also known as larger samples