SCMA Chapter 7 Sampling

A researcher selects every 10th student from an alphabetical list of 2,000 students after a random starting point. Which sampling technique is this?

C) Systematic sampling

A researcher wants to make conclusions about all undergraduate students at a university. They survey 600 undergraduate students. What do the 600 students represent?

B) The sample

A researcher uses her Instagram account to survey 400 university students and claims the findings represent all university students in Ontario. What is the main problem with this claim?

B) The participants were not selected using probability sampling.

In probability sampling, every element of the population has a known and equal chance of being selected.

True

Random sampling and random assignment are the same thing.

False

Match the sampling technique with its description: Simple Random

The researcher randomly selects elements from a full list of the population.

Match the sampling technique with its description: Stratified

The researcher divides the population into subgroups and draws a sample from each.

Match the sampling technique with its description: Cluster

The researcher randomly selects groups, then randomly selects elements from within those groups.

Match the sampling technique with its description: Snowball

Participants are asked to refer other potential participants.

Sampling

The process of selecting observations that will be analyzed for research purposes; selecting a subset of a group of interest and drawing conclusions from it.

Population

The cluster of people, events, things, or phenomena you are most interested in; who or what you want to say something about at the end of your study.

Sample

The cluster of people or events from which you will actually gather data.

Sampling Frame

A list of every member of the population from which a sample is drawn.

Homogeneous Group

A group that is the same on the characteristic being studied; any sample will do.

Heterogeneous Group

A group with diversity on the characteristic being studied; sampling becomes central to reflect that variability.

Representativeness

A sample that resembles the population it was drawn from in all the ways that matter for the research.

Generalizability

The idea that results tell us something about a group larger than the sample itself; key feature of probability samples.

Probability Sampling

Sampling where a person's likelihood of being selected is known; used to generate a statistically representative sample.

Non-Probability Sampling

Sampling where the likelihood of being selected is unknown; the method of choice when some participants are more useful than others.

Random Selection

The core principle of probability sampling; chance governs selection and every sampling element has an equal probability of being selected.

Sampling Error

The degree to which your sample deviates from the population's characteristics; the difference between sample results and actual population parameters.

Random Error

Error due to chance; cannot be controlled, only estimated and reported.

Systematic Error

Bias in selection that makes particular individuals more likely to be chosen than others; fixable.

Sampling Ratio

Sample size divided by population size (n/N); also the sampling fraction used in proportional stratification.

Simple Random Sampling

Randomly selects elements from a sampling frame; every element has the same probability of being selected.

Systematic Sampling

Selects every kth element from a sampling frame after a random start; k is the selection interval.

Selection Interval (k)

Population size divided by desired sample size; the distance between selected elements in systematic sampling.

Periodicity

The tendency for a pattern to occur at regular intervals; causes systematic sampling to fail when the frame is cyclical.

Stratified Sampling

Divides the population into relevant subgroups, then draws a sample from each subgroup.

Proportional Stratification

Each subgroup's sample size is proportionate to its size in the population; each subgroup has the same sampling fraction.

Disproportional Stratification

Subgroup sizes are not proportionate; two or more strata have different sampling fractions; used to compare small subgroups.

Cluster Sampling

Samples groups (clusters) of population elements first, then selects elements from within those groups.

Multi-Stage Cluster Sampling

Choosing one or more clusters at random and sampling everyone within the chosen cluster.

Purposive Sampling

Begins with specific perspectives to examine, then seeks out participants covering that full range; also called judgemental sampling.

Snowball Sampling

You know one or two people to include, and rely on them to identify others; also called chain referral sampling.

Quota Sampling

Identifies categories that matter, builds subgroups, and decides how many to collect from each; quotas set before sampling begins.

Convenience Sampling

Collects data from whoever is most conveniently accessible; also called haphazard or availability sampling.

Theoretical Sampling

Collecting and analyzing simultaneously, deciding what to collect next, continuing until theoretical saturation.

Theoretical Saturation

No new relevant data emerge and relationships among categories are well established.

Sampling Bias

When elements selected for inclusion do not represent the larger population from which they were drawn.

Non-Response Bias

When only those with strong opinions return surveys, limiting claims about patterns found in the data.

WEIRD Societies

Western, Educated, Industrialized, Rich, and Democratic societies; criticism that research over-relies on these samples.

Random Sampling

How you select a sample from a population; decides who ends up in your study at all.

Random Assignment

How you allocate participants you already have to conditions; decides who gets the treatment and who is in the control group.

Element

The individual unit about which data is collected and analyzed (e.g., a person, a document).

Content Analysis Sampling

Sampling documents, broadcasts, or posts rather than people; the same logic of frames, intervals, and strata applies.

Time Sampling

Observing at random times through the day when no sampling frame exists for structured observation.