Different types of samples are obtained depending on the method by which elementary units are selected for observation. These include two major types of samples, which are: non-probability samples and probability samples. Non-probability samples include: convenience samples, and judgement samples; while probability samples include various forms of random samples.
A convenience sample (also known as accidental sample, grab sample, or availability sample) is a non-probability sample, constituted by selecting the most conveniently located or easily accessible elementary units. This kind of samples is preferred by many researchers because it can be accessed fast, inexpensive, easy and the subjects are readily available.
Examples of a convenient sample is student volunteers as subjects for the research, subjects that are selected from a clinic, a class or an institution that is easily accessible to the researcher. One disadvantage of this type of samples is that, it is unlikely that a convenience sample of a statistical population is representative of it in the sense that valid inferences can be drawn from the sample about the population.
A judgement sample (also called purposive sample or authoritative sample) is a non-probability sample, where the researcher chooses the elementary units using personal judgement based on prior experience. Judgment sample is most effective when only a limited number of individuals possess the trait that a researcher is interested in.
For example, a researcher may decide to draw the entire sample from one “representative” city, even though the population includes all cities.
Most important, because it avoids the problem of unrepresentativeness, is the random sample, or probability sample, which is a subset of all elementary units, or of an associated population of their characteristics, that is chosen by a random process that gives each unit of the frame or associated population a known positive (but not necessarily equal) chance to be selected. If properly executed, the random selection process allows the investigator no discretion as to which particular units in the frame or population enter the sample. As a result, such a sample tends to maximize our chances of making valid inferences about totality from which it is drawn.
Because random samples are so important, we must look at them in some detail. Many types of random samples exist; the most important ones are introduced below.
Simple Random Sampling
A simple random sample is a subset of a frame, or of an associated population, chosen in such a fashion that every possible subset of like size has an equal chance of being selected. This procedure implies that each individual unit of the frame or population has an equal chance of selection as well.
The Systematic Random Sampling
The systematic random sample is a subset of a frame, or of an associated population, chosen by randomly selecting one of the first k elements and then including every kth element thereafter. If this procedure is employed, k is determined by dividing population size, N, by desired sample size, n.
The Stratified Random Sample
Sometimes the frame or population to be sampled is known to contain two or more mutually exclusive and clearly distinguishable subgroups or strata that differ greatly from one another with respect to some characteristic of interest, while the elements within each stratum are fairly homogeneous. In such circumstances, one can select a stratified random sample, which is a subset of a frame, or of an associated population, chosen by taking separate (simple or systematic) random samples from every stratum in the frame or population, often in such a way that the sizes of the separate samples vary with the importance of the different strata.
The Clustered Random Sample
Finally, there are occasions when the frame or population to be sampled is naturally subdivided into clusters on the basis of physical accessibility. In such circumstances, one can select a clustered random sample, which is a subset of a frame, or of an associated population, chosen by taking separate censuses in a randomly chosen subset of geographically distinct clusters.
Someone who wanted to sample the residents or shops of a city, for example, might divide the city into blocks, randomly select a few of these (by any of the methods previously mentioned), and then interview every resident or shop owner within the chosen blocks.
Thank you for reading. If you have any questions, leave a comment below.
Thank you for sharing!