Sample size refers to the number of observations that will be included in a statistical sample.
A sample is a collection of objects, individuals or phenomena selected from a statistical population usually by a given procedure.
The sample size affects the following:
Confidence and Margin of Error - The more a population is varied, the higher the unreliability of the calculations or estimates. In the same vein, as the sample size increases, we have more information. The more information we have, the less we error or uncertainty we have.
Power and Effect Size - Upping the sample size enables one to detect variances. Put differently, on the balance of probability, an average obtained on a larger sample size will exceed the average real than average collected on a smaller sample size.
Size Versus Resources - An overtly large sample will lead to a waste of resources that are already scarce and (where human subjects are involved) could expose them unecessarily to related risks.
A study should only be carried out only if, on the balance of probability, there is a fair chance that the study will produce useful information.
Variableness - Population Sampling makes room for variableness. Variableness ensures that every member of the population has a probability of being represented in the sample.
