Simple Random Sampling
Simple random sampling, or random sampling without replacement, is a sampling design in which is distinct units are selected from the N units in the population in such a way that every possible combination of n units is equally likely to be the sample selected.
The sample may be obtained through is selections in which at each step, every unit of the population not already selected has an equal chance of selection.
Equivalently, one may make a sequence of independent selections from the whole population, each unit having an equal probability of selection at each step, discarding repeat selections and continuing until n distinct units are obtained.
A simple random sample of n = 40 units from a population of N = 400 units is depicted in Figure below:
Designs other than simple random sampling may give each unit an equal probability of being included in the sample. But only with simple random sampling, each possible sample of is units has the same probability.
SRS will produce a sample that is representative of the population. The process will not select any one area of the population over another. SRS will not choose an individual to a sample in this population. There is no systematic selection of an individual. The sample selection is random, meaning that there is no influence on the selection of an individual. The probability of being selected for a sample is equal for all individuals. This is important because SRS does not select on demographic characteristics, such as age or race.
SRS is the simplest form of sampling. If you’ve ever used a random number generator, then you’ve done SRS. Random sampling is also called ‘simple random sample’ or ‘simple random selection’, and you can use it whenever you need to sample objects from a population. For example, when you are trying to figure out how many members of a particular type (group) of objects there are in a group of objects.