Simple Random Sampling (SRS): In this method, every member of the population has an equal probability of being selected. It is typically performed by assigning a unique number to every member in a sampling frame and using a random number generator to pick the required sample size.
Systematic Sampling: This involves selecting members from a sampling frame at regular intervals, such as every person. The starting point is chosen randomly between and , where , ensuring a spread across the entire list.
Stratified Sampling: The population is divided into mutually exclusive groups called strata (e.g., age groups or genders). A random sample is then taken from each stratum in proportion to its size in the population, ensuring that all sub-groups are represented fairly.
Quota Sampling: Similar to stratified sampling, the population is divided into groups, but the selection within those groups is non-random. Researchers are assigned a 'quota' to fill (e.g., 20 men and 20 women) and can choose any individuals who fit the criteria until the quota is met.
Opportunity (Convenience) Sampling: This method involves selecting individuals who are easiest to reach or most available at the time of the study. While highly efficient and low-cost, it is prone to significant bias as the sample is unlikely to be representative of the broader population.
Cluster Sampling: The population is divided into naturally occurring groups or 'clusters' (like schools or geographic regions). A few clusters are chosen at random, and then every member within those selected clusters is surveyed.
| Feature | Stratified Sampling | Quota Sampling |
|---|---|---|
| Selection | Random selection within groups | Non-random selection within groups |
| Sampling Frame | Requires a complete list of the population | Does not require a sampling frame |
| Bias | Minimizes selection bias | High risk of researcher bias |
| Cost/Speed | More expensive and slower | Cheaper and faster |
Identify the Method: When a scenario mentions a 'list' or 'database', look for Systematic or Simple Random sampling. If 'groups' or 'categories' are mentioned, determine if the selection within those groups was random (Stratified) or not (Quota).
Evaluate Bias: Always check if the sampling frame excludes certain groups (e.g., a phone book excludes people without landlines). In systematic sampling, watch for periodic patterns in the list that might coincide with the sampling interval, which can lead to a biased sample.
Justify Choices: If asked to recommend a method, consider the constraints. Use Census for small populations where accuracy is paramount; use Sampling for large populations or destructive testing. Choose Stratified when you want to ensure specific sub-groups are represented.
Sampling Frame vs. Population: Students often confuse the two. The population is the theoretical group of interest, while the sampling frame is the actual list used. If the list is missing members of the population, the sample will suffer from undercoverage bias.
Non-Response Bias: Even with a perfect random sample, bias occurs if the people who choose not to respond have different characteristics than those who do. This is a common issue in postal or email surveys.
Self-Selection: This occurs when individuals volunteer themselves for a study (e.g., online polls). These samples are almost never representative because people with strong opinions are more likely to participate.
