Sampling and Types of Sampling in Sociology: 22 MCQs with answers

The population

The population (or universe) is the entire group the researcher wants to draw conclusions about. The sample is the subset actually studied, and the sampling frame is the list from which the sample is drawn.

The sample

The 500 women actually selected and studied form the sample. The population is all urban working women in the state, and the sampling frame would be the list from which the 500 were drawn.

The sampling frame

The sampling frame is the list or map from which the sample is drawn — such as a voter roll, school register, or census block list. A weak frame ruins even a clever sampling technique.

Probability sampling

Probability sampling gives every unit a known, non-zero chance of selection, and selection is random. This is what makes statistical generalisation possible.

Simple random sampling

Simple random sampling gives every unit an equal chance of selection, typically through a lottery or random number generator.

Systematic sampling

Systematic sampling selects every $k$-th unit after a random start. Here, $k = 10$.

Stratified sampling

Stratified sampling divides the population into homogeneous strata (by gender, caste, income) and samples randomly within each stratum, taking a few from every group.

Cluster sampling

Cluster sampling randomly selects whole clusters and studies everyone inside them — taking all from a few groups.

Snowball sampling

Snowball sampling uses referrals from existing respondents to reach hidden or hard-to-reach populations such as undocumented migrants or street children.

Convenience sampling

Convenience sampling uses the most easily available respondents — in this case, whoever happens to walk by the researcher's own college.

Quota sampling

Quota sampling is a non-probability method: fixed quotas by category are filled by convenience, so not every unit has a known chance of selection.

True

In **probability sampling**, every unit of the population has a known and non-zero chance of being selected, which is what makes statistical generalisation possible.

Purposive sampling

Purposive (judgement) sampling deliberately selects information-rich cases that suit the study's purpose — ideal for a deep case study of one village.

Stratified takes a few from every group; cluster takes all from a few groups.

In stratified sampling you take a few from every group (strata); in cluster sampling you take all from a few randomly selected groups (clusters). Remember: strata = sample within all; clusters = sample whole clusters.

Multi-stage sampling

Multi-stage sampling combines several probability methods in successive stages — here, districts, then villages, then households.

Probability sampling gives every unit a known, non-zero chance of selection, so sampling error can be estimated.

In probability sampling every unit has a known, non-zero chance of selection, which allows researchers to estimate sampling error and generalise with confidence. Non-probability sampling gives no such known chance.

Stratified sampling divides the population into homogeneous strata and samples randomly within each stratum, whereas cluster sampling selects entire clusters and studies all units within them.

The correct option accurately describes that in stratified sampling, the population is divided into homogeneous groups (strata) and samples are taken from each, while in cluster sampling, entire groups (clusters) are selected and all members within those clusters are studied.

Stratified sampling

The researcher is using stratified sampling because she divides the population into homogeneous strata (income levels) and then randomly selects individuals from each stratum.

It minimizes costs and maximizes coverage of diverse groups.

This approach minimizes costs and maximizes coverage of diverse groups by allowing the researcher to efficiently sample different layers of the population while maintaining representativeness.

Snowball sampling

Snowball sampling is the most appropriate method for studying hidden populations because it relies on existing respondents to refer others within the community, which is crucial when a sampling frame is unavailable.

The sample lacks representativeness.

The primary concern is that the sample lacks representativeness since it is drawn from a single source (one online forum), which may not reflect the broader population's views.

Probability sampling allows for strong generalization, while non-probability sampling cannot generalize statistically.

Probability sampling allows for strong generalization because every unit has a known chance of selection, while non-probability sampling does not support statistical generalization due to unknown selection chances.