(a) Simple random sampling.

• System random sampling is the purest form of probability sampling, wherein every individual in the population has equal chance of being selected. The biggest advantage of simple random sampling is the lack of bias and skewness in the data. It is highly likely simple random sampling method produces normally distributed data. However, simple random sampling can be costly, labor-intensive and time-consuming.

(b) Systematic sampling.

• Systematic random sampling is a probability sampling method wherein a number (e.g. n) is first randomly generated and then every n^th member of the population is selected to be included in the sample. Advantages of systematic random sampling method include removal of bias or subjectivity from the selection process, retaining randomness, consistency and reduction of the likelihood of data contamination. However, systematic sampling will work meaningfully only if sample sizes are large and if a full and accurate list of the population is available.

(c) Stratified sampling.

• Stratified random sampling is a probability sampling method wherein the individuals in the population are first divided in subgroups called strata based on shared characteristics and then individuals are randomly drawn from each stratum to be included in the study sample. The biggest advantage of stratified sampling is that it is an effective method of sampling for studies that analyze differences between subgroups (e.g. differences between males v. females). Also, because of initial stratification, stratified sample yields greater accuracy and lower margins of error compared to a simple random samples of the same sample size. The biggest disadvantage of a stratified sample is that it is labor-intensive and also could involve complex calculations.

(d) Cluster sampling:

• While stratified samples are internally homogeneous and externally heterogeneous, cluster samples as externally homogeneous and internally homogeneous. Population is divided into clusters, with each cluster supposedly representative of the population. Thereby, a few clusters are randomly drawn from the population and included in the sample. Cluster sample has wider margins of error than some of the other probability sampling methods. The data has a potential to be more contaminated. However, cluster sampling method is effective for quick surveys to question a few units of the population that represent the entire population. Cluster samples are also cost-effective and often used in US presidential election exit polls.