08/10/2025
PROBABILISTIC SAMPLING METHODS
These are sampling methods in which the researcher is required to utilize the principle of randomization (or chance procedure) in at least one of the stages of the sample process. There are four basic types, namely: Simple Random Sampling, Systematic Random Sampling, Stratified Sampling and Cluster Sampling.
a) SIMPLE RANDOM SAMPLING
In this method, the entire process of sampling is guided by chance procedures. It is the most scientific of sampling methods and is the model on which scientific sampling is based. However, it is not commonly used in the social sciences and the humanities because it can sometimes lead to unrepresentative samples in circumstances in which diversities in the population have to be meaningfully reflected in the sample being drawn up.
Procedure for simple random sampling is as follows:
Firstly, secure a list of the entire population in which every subject is listed only once. The list is the sampling frame.
Secondly, number every subject in the list
Third, use a mechanical device (balloting, dice, table of random numbers) to select the subjects that will constitute the sample.
b) SYSTEMATIC RANDOM SAMPLING
Often confused with the simple random method. It is, however, more systematic as the name suggests.
The procedure is as follows:
1. Secure a list of the entire population in which every subject is listed once.
2. Number every subject in the list
3. Determine the sample size you want to draw from the population.
4. Calculate the sampling interval, by dividing the population size by the proposed sample size.
5. Randomly (using a mechanical device) draw from the sampling frame the first member of your sample. This first member must be drawn from the section of the population not above (but could be equal to) the number that corresponds to the sampling interval.
6. Beginning with the selected case number indicated above, go down the list, systematically adding the sampling interval to selected cases until the required number of cases to fill the sample size has been attained.
c) STRATIFIED RANDOM SAMPLING
Stratified sampling is so called because it requires that the population be divided into strata before sampling takes place within each stratum. Sampling fraction for each stratum could either be equal (if, in the study under consideration, the major interest lies in comparing strata-such as male/female, high IQ/low IQ), or unequal (if the major interest of the study is to make findings that are generalizable or applicable to the population, e.g lower/middle/high management.)
The procedure is as listed below:
1. Compile a list of the population in which every subject is listed only once
2. Divide all subjects into groups or strata; these strata must be defined in such a manner that no subject appears in more than one stratum
3. Take either a simple random or a systematic sample from within each stratum proportional to the strata’s strength/value in the population.
4. Decision on proportional reflection of strata of the population in the sample depends on the goal of the study under consideration
d) CLUSTER SAMPLING
Cluster sampling is the successive random sampling of units and subunits of the population.
Remember, in Stratified sampling we divided the population into groups called strata and then sampling subjects from within the strata.
Cluster sampling on its own part involves dividing the population into large numbers of groups called clusters and then successively sampling such clusters from very large to the smallest of clusters before finally sampling subjects. The procedure is as follows:
1. Define the population.
2. Identify all possible clusters in the population from largest to smallest.
3. Successively sample clusters from the very large groups to the large groups to subgroups etc. until you get to the stage of individual subjects.
4. Randomly select the subjects.
5. This is a very useful method when dealing with a large population or when a list at the macro levels of sampling will be difficult, if not impossible, to compile
The Economics Tutor
