n

The sample size is traditionally labeled n, as opposed to the total population size, which is termed N. The sample size, n, can refer to either the original number of population elements selected into the sample (sometimes called the “designated sample size” or “sampling pool”), or it can refer to the final number of completed surveys or items for which data were collected (sometime called the “final sample size” or “final sample”). In the same vein, it could refer to any number in between such as, for example, the number of elements that have been sampled and contacted but not interviewed. Or it could refer to the number of elements for which complete data are available. Another interpretation or use of the term n is the number of elements on the data file and available for analysis.

It is almost always true that n is smaller than N and usually by orders of magnitude. In fact, the ratio (n/N) is often referred to as the sampling fraction. Often the population size N is so large relative to n that one can safely assume that with replacement sampling holds even if in practice without replacement sampling is implemented. The relative sizes of n and N also play a role in determining whether the finite population correction factor [1 − (n/N)] is sufficiently different from 1 to play a role in the calculation of sampling variance.