SAMPLING TECHNIQUES

            Typically, a researcher wants to select a sample that is like the population of interest in a number of characteristics, so that it can be considered representative of the population.  If it has over or under-represented segments of the population, so tht the sample’s members have different characteristics from those of the population, it is a biased sample.

Figure 5.1  The Relationship Between a Population and a Sample (p. 116)

Sampling:  The process of selecting individuals to participate in a research study.

In probability sampling, the entire population is known, and sampling is done by a random process.

Simple Random sample: It is selected in such a way so that everyone in the population has an equal chance of being selected. The following steps are required:

1.      Clearly defining the population.

2.      Listing all the members of the population.

3.      Using a random process to select individuals from the list.

 Even though the above procedure guarantees an unbiased sample in the long run, in the short run there are no guarantees.
Systematic sampling:  A sample is obtained by selecting every nth participant from a list of the total population, after a random start.  As a probability sampling method this method insures a high degree of representativeness.

Figure 5.3  A Systematic Sampling Technique (p. 122)

Stratified random sampling:  This procedure ensures that each subgroup (stratum) in a population is represented equally in a sample.

Figure 5.4  The Population of a Major City Shown as Different Layers or Strata Defined by Annual Income (p. 123)

Proportionate stratified random sampling:  This is like the above, but it takes into account the proportion of the population that corresponds to each subgroup.

Cluster sampling:  Whenever well-defined clusters exist within the population of interest, we can randomly select clusters, rather than individuals.

In nonprobability sampling, the population is not completely known, and the sampling method is based on factors such as common sense or ease.

Haphazard (convenience) sample:  the sample is based on convenience, such as the availability of participants (e.g. volunteer participants).