Simple random sampling
Just like multi-stage sampling, simple random sampling is also a probabilistic sampling technique. In this sampling method, the population frame is prepared, and the selection of the subjects or respondents for the study is random. Besides, just like multi-stage sampling, smaller sample sizes can be culled from a larger population using this method. Based on the smaller sample size, generalizations can be arrived at about the larger group (Khan, 2020). It is different from the multi-stage sampling method in that it does not require more steps or for the population to be divided into sub-populations because of the concept of randomness. However, one must also note that a biased sample can result in the drawing of incorrect conclusions concerning the broader population.
Why is this also appropriate?
This type of sampling is appropriate for this study because it provides each person in the population with the same probability of being included in the sample. The equal chance of selection arises for the fact that the individuals comprising the sample are selected at random. Therefore, it will be useful in answering the research questions. This method can be useful for countries whose population size is relatively small, have a high infection rate, and has been affected by the virus. Furthermore, when Covid-19 incidences are rare concerning the population size, there is an increase in the likelihood of selecting and basing generalizations on an ineffective sample. Besides, the probability of selection depends on the population. The selection can be computer-generated in case of a larger population or generated manually in a smaller population (Khan, 2020). This method is easy to use and provides an accurate representation of the larger group. It is arguably the easiest method of extracting a research sample from a larger population.
Which method do you think is better? Why?
In Covid-19 research, there is a need for a cost-effective strategy. When dealing with a large study population, using a standard simple random sampling procedure becomes tedious. In such situations, it is common for researchers to adopt multi-stage sampling (Uthayakumaran & Venkatasubramanian, 2015). The multi-stage sampling method is useful in statistics because it utilizes small sampling units when taking samples at each stage. Therefore, although it is complex as a cluster sampling method, it enables the population’s division into clusters or groups, allowing for random elements selection from each cluster.
This method reduces the research cost and improves survey speed. As a probability sampling technique, the sample size reduction at each stage is one of its characteristics as the sampling is done in several stages. Also, the survey sample can be found more conveniently (Hankin et al., 2019). Lastly, compared to random sampling in a larger population, it is more accurate. However, with the same sample size, a simple random sample is more accurate. Also, using multi-stage sampling is disadvantaged because of the difficulty linked to more testing.