Explain the probability sampling strategies with examples. (UPSC CSE Mains 2019 - Sociology, Paper 1)
Probability sampling is based on random selection of units from a population. In other words, the sampling process is not based on the discretion of the researcher but is carried out in such a way that the probability of every unit in the population of being included is the same. For example, in the case of lottery, every individual has equal chance of being selected. Some of the characteristics of a probability sample are:
- each unit in the sample has equal probability of entering the sample,
- weights appropriate to the probabilities are used in the analysis of the sample, and
- the process of sampling is automatic in one or more steps of the selection of units in the sample. Probability sampling can be done through different methods, each method having its own strengths and limitations.
There are four broad methods of probability sampling:
- Simple random sampling: This is the “pull a name out of a hat” method, in which all members of the larger population have an equal chance of being selected. The selection is done randomly. The drawback to this method is that it’s prone to bias. If the sample size is too small, relative to the larger frame, we’re less likely to pick reliable random samples.
- Interval sampling: This method assigns every member of the population a number, then selects individuals at regular intervals. For example, every tenth person becomes part of the sample. There are certain drawbacks to this method, too: it might not be as random as simple random sampling, and if there are any hidden patterns in the larger population list, it could skew your results.
- Stratified random sampling: This method divides the larger frame into specific groups that do not overlap, but when put together, they reflect the overall population. This could be groups like “have created a user account and made a purchase” vs. “have created a user account but have not made a purchase.” Common stratified characteristics include gender, age, ethnicity, and other mutually exclusive categories. Once we’ve stratified your population, we can use simple random sampling to select people from each group, proportional to the overall population.
- Cluster sampling: Cluster sampling separates the larger population into subgroups—but unliked stratified random sampling, the clusters are smaller versions of the overall population. Pollsters can randomly select entire clusters, or randomly select individuals from each cluster. Clusters might be sorted by organizations (universities, corporate offices) or geographic locations (states, cities, counties). The drawback to cluster sampling is that there’s no guarantee every cluster actually represents the overall population.
Next
previous
Latest News
EDITORIALS & ARTICLES
General Studies