SAMPLING

Sampling is examining an entire population based upon the collection of data from a subset of that population. The idea is that by taking a sample, you can make inferences about the entire population.

Sampling can be random or purposeful. Random sampling occurs when every item in the population has an equal chance of being selected. Purposeful sampling is using a specific criterion (e.g., everyone with blue eyes) to select an item.

Samples can be segmented according to some grouping and class. Samples can also be taken from homogeneous and heterogeneous populations. When sampling from a heterogeneous population, however, homogeneity can be obtained through subdivisions (e.g., sex and race).

Regardless of the type of sampling, reliable sampling has three common characteristics. First, the sample is randomly selected. Second, the sample must be representative of the population. Third, bias should be minimized.

Sampling is more beneficial than examining an entire population because it is cheaper and faster and has a history of success behind it. Furthermore, it can be automated and can be used in a wide variety of environments.

for Sampling

• Determine the population to sample.
• Determine the desired confidence level.
• Determine the size of the sample.
• Define the class intervals, if applicable.
• Use a random number table to select the first sample.
• Determine the type of sample.
• Develop inferences from the results.