Sample, target population, sampling method
Three terms underpin this statement, and mark schemes reward keeping them apart. Target population — the whole group the researcher wants the results to apply to, e.g. all UK Year 11 students. Sample — the participants actually studied, drawn from it. Sampling method — the procedure used to select the sample. It matters for generalisation: a sample that fairly reflects the population is representative, so findings generalise back to it.
Four methods: how participants are picked
Learn each of the four methods by its procedure. Random — every member of the population has an equal chance of selection. Stratified — the population is split into subgroups (strata) chosen in proportion to its size. Volunteer — participants put themselves forward. Opportunity — the researcher uses whoever is available. Signature: equal chance → random, subgroups → stratified, coming forward → volunteer, convenience → opportunity.
Each method: one strength, one weakness
Know a strength and weakness of each. Random: removes researcher bias, but needs a full list and can still be unrepresentative by chance. Stratified: subgroups appear in proportion, so usually the most representative, but time-consuming. Volunteer: quick and easy, but volunteers may share traits (keen), risking bias. Opportunity: fastest and most convenient, but only those available are used. Pattern: controlling bias costs time; convenience risks bias.
Drawn from real examiner reports.
Volunteer and opportunity swapped
These two are mixed up more than any other pair. The distinction is who does the choosing: in volunteer sampling the participant comes forward (e.g. replying to an advert); in opportunity sampling the researcher approaches whoever is available. If the person put themselves forward it is volunteer; if the researcher used who was there, it is opportunity.
Volunteer confused with opportunity is recorded in November 2020 Paper 2 Q3b.
Opportunity left vague or unnamed
Where candidates cannot name the method they often leave it blank or describe it loosely. Opportunity is the one most often left unidentified. Tie the answer to its signature: the researcher used whoever was available at the time, such as shoppers passing by. Because only those present could be chosen it is not random — people not there had no chance of selection.
Opportunity confused with other methods or left blank is recorded in November 2021 Paper 2 Q02b.
Random defined as "random"
Writing that random sampling means the participants were chosen at random earns nothing, because it restates the term instead of explaining it. The creditworthy answer names the procedure: every member of the target population has an equal chance of selection — for example, names drawn from a hat, or a random number generator on a full list.
Random defined tautologically as "random" is flagged in June 2022 Paper 2 Q3b.
Stratified without proportional subgroups
Stratified is the method most often half-right. A full definition has two parts: the population is divided into subgroups (strata) (age, gender) and participants selected in proportion to each subgroup's size. Weak answers drift into opportunity or random, dropping the proportional idea. Without subgroups and in proportion, it is not stratified.
June 2024 Paper 2 Q2b records that stratified sampling means dividing the target population into subgroups and selecting a representative number from each, with weak answers drifting into opportunity or random.
A bigger sample is not automatically better
A common suggestion is use a bigger sample, assuming more people makes a study more representative. Examiners treat this as a misunderstanding of generalisability: representativeness depends on the nature of the sample, not its size. A hundred keen volunteers are no more representative than ten. What fixes it is a method reflecting the population, e.g. stratified.
June 2019 Paper 2 Q3c records that increasing sample size is not automatically an improvement, and June 2022 Paper 1 Q5b that "more in a sample will make it more representative" misunderstands generalisability — it is the nature of the sample that matters.
"Random" does not mean haphazard
In everyday speech random means haphazard, so students think it means grabbing whoever they meet — actually opportunity sampling. In psychology random is precise: every member of the population has an equal chance of selection, needing a deliberate procedure. Contrast: opportunity uses whoever is available; random gives everyone an equal chance.
Volunteer sampling is not the fairest
Because volunteers agree to take part, students assume the sample is fair. The opposite applies: self-selection is a source of bias. Volunteers tend to share traits (motivated, interested), so the sample can be unrepresentative. Its strength is being quick and easy to gather willing participants. It is a trade-off: convenience at the cost of volunteer bias.
Name the method from the procedure
Name the method from the selection procedure, not a guess. Find how participants were chosen, then match the signature: equal chance for all → random; proportional subgroups → stratified; people coming forward → volunteer; whoever was available → opportunity.
Justify, do not just identify
If asked for a strength or weakness, name it and say what it does to this study. Opportunity sampling is quick is bare identification; …but only shoppers in one centre were used, so it may not represent all adults earns it. AO3 cannot be awarded without AO2.
Describe the difference: use a connective
When asked to describe the difference between two methods (often volunteer vs opportunity), give one comparative sentence, not two definitions side by side. Two definitions read as an implicit comparison and score half; a connective such as whereas earns the second mark.
Target population — the whole group the researcher is interested in and wants the results to apply to.
Sample — the participants actually studied, drawn from the target population.
Sampling method — the procedure used to select the sample from the target population.
Representative sample — a sample that fairly reflects the target population, so the findings can be generalised back to it.
Full notes, flashcards, Q&A and the topic quiz for every premium subject.
Premium plans are US$8.99/month or US$49.99/year — first month free.
Studying with a parent's blessing? Show them this.
