UGC NET Questions (Paper – 1)

Stratified sampling involves dividing the population into strata based on relevant characteristics such as age, gender or region, and then selecting samples from each stratum, usually by random methods. This approach ensures that key subgroups are adequately represented in the sample. It can increase precision and allow for subgroup comparisons. Hence, the technique described in the stem is correctly termed stratified sampling.

Option A:
Cluster sampling selects intact groups such as schools or villages as the initial units and then studies all or some members within them; it does not primarily aim at forming homogeneous strata for representation. Therefore, cluster is not the correct completion.

Option B:
Option B, stratified sampling, focuses on homogeneity within strata and heterogeneity between them in relation to the variable of interest. By drawing from every stratum, it guards against underrepresentation of smaller but important groups, which matches the description in the question.

Option C:
Systematic sampling chooses every kth unit from a list after a random start and does not inherently ensure representation of specific homogeneous subgroups. Thus, it is not the best answer here.

Option D:
Quota sampling is a non-probability method where quotas for categories are filled using convenience selection, so it lacks the random component that defines stratified probability sampling. It therefore does not fit the stem.

Systematic sampling begins by choosing a random starting point on an ordered list of population elements and then selecting every kth element thereafter, where k is the sampling interval. This procedure is simple to implement and can approximate random sampling if the order of the list is not correlated with the variables of interest. It also ensures a spread of the sample across the entire frame. Therefore, the method described in the stem is correctly called systematic sampling.

Option A:
Option A, systematic sampling, relies on a fixed numeric step to move through the sampling frame, making selection predictable once the start and interval are set but still probabilistic. Its efficiency and simplicity match the description of selecting every kth element.

Option B:
Convenience sampling is a non-probability method where respondents are chosen because they are easy to reach, without using a fixed interval or random starting point. Thus, it is not appropriate here.

Option C:
Cluster sampling selects intact groups or clusters, not individual elements at regular intervals from a list. It is based on groupings rather than on a numeric step, so it does not fit the stem.

Option D:
Purposive sampling is a judgment-based, non-probability method targeting specific information-rich cases and does not involve fixed intervals or an ordered frame. Hence, it is not the correct completion.