Probability Sampling and its Types
Each member of the population has a known probability of being chosen for the sample in this kind of sampling. Each person has a good probability of being chosen for a sample when the population is quite homogeneous.
For example, if we were to choose some rice from a bag of rice, there is a good likelihood that each grain would be chosen. As a result, the sample taken will be an accurate representation of the entire rice bag.
Since every element of the population is the study’s target participant, the population functions as a very homogenous group in this study.
What are the types of probability sampling?
- Simple random sampling:
The sample members are chosen at random and solely by chance in this sort of sampling. As a result, the sample’s quality is unaffected because each member has an equal probability of being chosen. The optimal population for this kind of sampling is quite homogeneous. This form of sampling can be done in one of two different ways:
- Simple random sampling with replacement (SRSWR)
- Simple random sampling without replacement (SRSWOR).
Simple random sampling with replacement (SRSWR):
Choosing “n” units out of “N” units one at a time so that each item has an equal probability of being chosen, or 1/N, at each stage of the recruitment process.
Simple random sampling without replacement (SRSWOR):
Choosing “n” units out of “N” one at a time at any point of the sampling process so that each unit on the left has a 1/N chance of being chosen as a sample.
- Cluster sampling:
In cluster sampling, diverse population subgroups are considered clusters, and individuals from each cluster are randomly chosen. Stratified sampling and cluster sampling are distinct from one another. In stratified sampling, the analyst divides the population into different groups based on factors such as age, sex, profession, and so forth, whereas in cluster sampling, researchers randomly choose from pre-existing or naturally occurring groups or clusters, such as towns within a township or families within society. In this strategy, we first create clusters based on our needs, and then researchers choose samples using methodical or simple random sampling.
- Stratified random sampling:
In this kind, the population is first divided into smaller groups called strata based on their shared characteristics, and then individuals are randomly chosen from each group or stratum. Thus, the goal is to create a sample that represents the population while also addressing the problem of demographic homogeneity. Another name for this kind of sampling is random quota sampling. Age, socioeconomic status, country, religion, and other similar categorizations ought to be used.
There are two types of stratified sampling:
- With proportionate stratified random sampling, each stratum sample has the same sampling percentage and the representative sample is directly proportional to the total population of stratification.
- whenever the sample size is asymmetrical.
- Multi-stage Sampling:
Multistage sampling is what it is called since it has several steps, as the name would imply. The individuals are chosen at random from each smaller cluster after further subdividing each cluster of data into smaller clusters. Cluster sampling in this way is intricate.
Initially, groups within a population are chosen to form clusters -> Each cluster is then broken into smaller clusters -> and individuals are randomly chosen from each of these smaller clusters.