I often get asked how many people should we be sampling. How do you work this out?

Sampling can be a fraught process, yet it should be rather straightforward. In her 1999 book, Practical Evaluation Guide: tools for museums and other informal educational settings, Judy Diamond suggested that 96 visitors is a sufficient sample size to make generalisations and produce conclusions for a museum that has one million visitors per year, with a ten percent sampling error.

Also, issues of reliability and validity need to be accounted for - to read more about those Chapter Three of my thesis explains all.

Just came across this very useful table from the Survey Monkey blog - How Many People Do I Need to Take My Survey?. Lots of practical info here and a good case example.

Happy sampling everyone!