Sampling and sample design in HSC Community and Family Studies Core Research Methodology
“Sampling: the sample group and sample size, random, stratified and convenience sampling, and how sampling decisions affect the reliability, validity and generalisability of findings”
A sample is a smaller group selected to represent a larger population because studying everyone is rarely possible. Random sampling gives every member an equal chance and reduces bias; stratified sampling ensures subgroups are represented; convenience sampling is quick but unrepresentative. A larger, well-chosen sample improves reliability and the ability to generalise findings.
Jump to a section
What this dot point is asking
You need to understand what a sample is, the main ways to select one, how sample size matters, and how every sampling decision feeds back into the reliability and validity of the research. Sampling is examined directly in short-answer questions and is a key decision in the Independent Research Project.
Population and sample
The population is the whole group the research is about, for example all Year 12 students in a school. Studying every member is usually impossible because of time and cost, so the researcher selects a sample, a smaller subset chosen to represent the population. The quality of that representation decides how far the findings can be trusted and applied beyond the people actually studied.
Sample size
Sample size is the number of respondents. A larger sample generally produces more reliable, more generalisable results because it smooths out individual quirks and reduces the chance that a few unusual responses distort the picture. However, size must be balanced against the resources available and the method used. A questionnaire can handle hundreds of respondents, while in-depth interviews of the same number would be unmanageable for a student. The goal is a sample large enough to be credible yet realistic for the project.
Random sampling
In random sampling every member of the population has an equal chance of being selected, for example by drawing names or using a random number generator. Its strength is that it minimises selection bias and improves the chance the sample mirrors the population. Its weakness is that it requires a complete list of the population and can still, by chance, miss important subgroups in a small sample.
Stratified sampling
Stratified sampling divides the population into subgroups, or strata, such as age bands, year groups or genders, then samples from each so all are represented in proportion. This is useful when the research question depends on comparing groups, for example differences between male and female respondents. It produces a more representative sample than simple random sampling when subgroups matter, but it requires the researcher to know the relevant strata in advance.
Convenience sampling
Convenience sampling uses whoever is easiest to reach, such as the researcher's own class or friends. It is fast and cheap, which is why many student projects rely on it, but it is prone to sampling bias because the easy-to-reach group may not represent the wider population. If a project uses convenience sampling, the limitation must be acknowledged honestly when discussing the validity of the findings.
How sampling affects reliability and validity
Sampling decisions feed directly into the trustworthiness of research. A representative sample of adequate size improves reliability, because repeating the study would likely give similar results, and improves generalisability, because the findings can be applied to the wider population. A biased or tiny sample undermines validity, because the data may not reflect the population at all. In CAFS answers, strong students name their sampling method, justify it against their research question and resources, and state honestly how it limits the conclusions they can draw.
A student wants their IRP sample of students to represent a school of students made up of junior and senior students. Show how to design a representative sample.
Step 1: Choose a sampling method
Use stratified sampling, which divides the population into subgroups (strata) and samples from each, so each group is represented in proportion to the population.
Step 2: Calculate each stratum's share
Junior students: students. Senior students: students. These add to the target sample of .
Step 3: Select within each stratum
Randomly select juniors and seniors, so within each group every student has an equal chance, reducing bias.
Step 4: Link the design to trustworthiness
Explain that this proportional, random-within-strata design makes the sample representative, improving generalisability and reliability compared with a convenience sample that might over-represent one year group.
Generalisability depends on representativeness, not just size. A small random or stratified sample can be more trustworthy than a large convenience sample, because the convenience sample may systematically exclude part of the population.
Do not assume a bigger sample is automatically better. A large but biased sample, such as 300 responses all from one friendship group, still produces unrepresentative, low-validity findings. Markers reward attention to representativeness as well as size.
Exam-style questions
Questions in the style of NESA exam questions on this dot point, each with a worked answer. They are written by ExamExplained unless tagged "Past paper"; the year shows the paper a question is modelled on.
2024 HSC-style8 marksExplain how appropriate sampling can assist a researcher in achieving validity and reliability.Show worked answer →
For 8 marks, define the key terms and then clearly link sampling decisions to both validity and reliability with examples.
Validity means the research actually measures what it intends to measure. Reliability means consistent, repeatable results. Appropriate sampling underpins both.
- Sample group
- Selecting a sample that is representative of the target population (for example a cross-section across age, gender and location) means the findings genuinely reflect that population, which supports validity. A biased or convenience sample, such as only the researcher's friends, skews results and threatens validity.
- Sample size
- A sufficiently large sample reduces the effect of individual outliers and random variation, so repeated sampling would produce similar results, supporting reliability. A sample that is too small produces unstable findings that are hard to replicate.
- Sampling method
- Random or stratified sampling minimises selection bias and ensures key subgroups are proportionally included, improving both the validity and the generalisability of conclusions, while convenience sampling increases the risk of bias.
- Conclusion
- When the sample is representative, large enough, and chosen through an unbiased method, the data is both valid (measures the right thing) and reliable (consistent on repetition), strengthening the trustworthiness of the whole project.
2022 HSC-style6 marksExplain the importance of selecting an appropriate sample group and size when conducting research.Show worked answer →
A 6-mark answer should explain the role of both the sample group and the sample size, and why each matters.
- Sample group
- The sample group is the section of the population chosen to take part. Selecting a group that represents a cross-section of the target population ensures findings are valid and can be generalised. An unrepresentative group, for example only one gender or one age, introduces bias and means conclusions cannot be applied to the wider population.
- Sample size
- The sample size is the number of participants. A size that is too small may not capture the diversity of the population and is heavily influenced by outliers, reducing reliability. A larger, well-chosen size produces more consistent, repeatable and trustworthy data.
- Why it matters
- Together, an appropriate sample group and size reduce bias, improve reliability and validity, and allow the researcher to draw sound conclusions that answer the research question. Choosing poorly wastes time and resources and undermines the credibility of the whole project.