| 5% is a common choice.||%||The margin of error is a statistic expressing the degree to which the researcher believes the data may not represent the whole population.
A lower margin of error requires a larger sample size.|
| Typical choices are 90%, 95%, or 99%.||%||The confidence level is a statistic expressing the confidence the researcher has that the data truly represents the whole population.
A higher confidence level requires a larger sample size.|
| If you don't know, use 20000.||How many people are there to choose from for your random sample? The sample size doesn't change much for populations larger than 20,000.|
| The most conservative choice is 50%.||%||What do you expect the results will be for each survey question? If sample data is skewed highly to one end, the population probably is too. If you don't know, use 50%. This gives you the largest sample size.|
|This is the minimum recommended number of complete responses to every question on your survey. Your data will be valid, within the tolerances you specified, if you obtain a response from this many people to every question on your survey.|