ABSTRACT
The units can indeed form the human population of a country or region or town. But equally the word could be applied to the collection of all primary schools in Scotland in a study on education, to all first-division football matches in the last five years in a study of hooliganism, to all Concorde take-offs from a certain airport in a study of aircraft noise, and so on. Sometimes populations can be enumerated, that is to say, the individual units can be identified and listed. The population under consideration is conceptually infinite in size because additional units can always be found or generated experimentally. Sampling is the selection of some units of a population to represent the whole aggregate and hence statisticians must make certain that the sample members are as typical as possible in relation to the objectives of the study. The main disadvantage of using a sample is that statisticians have to tolerate a greater degree of uncertainty.
