Skip to main content
EnglandPsychologySyllabus dot point

How do psychologists select participants, work ethically and turn raw observations into usable data?

Sampling methods, ethical considerations, reliability and validity, levels of measurement, and recording, analysing and presenting data.

An OCR A-Level Psychology answer to sampling and data handling, covering random, stratified, systematic, opportunity and self-selected sampling, BPS ethics, reliability and validity, levels of measurement, and how to record, analyse and present qualitative and quantitative data for Component 1.

Generated by Claude Opus 4.815 min answer

Reviewed by: AI editorial process; not yet individually human-reviewed

Have a quick question? Jump to the Q&A page

Jump to a section
  1. What this dot point is asking
  2. The answer
  3. Examples in context
  4. Try this

What this dot point is asking

OCR expects you to select participants fairly, anticipate ethical problems, judge whether a study is reliable and valid, and turn raw observations into data you can analyse. These skills underpin every study on Component 2 and recur in the data-handling questions on Component 1.

The answer

Sampling methods

Random and stratified sampling give the most representative samples but take effort; opportunity and volunteer sampling are quick but biased (opportunity samples over-represent whoever is around; volunteers tend to be more motivated). The right method balances representativeness against practicality.

Ethical considerations

Reliability and validity

  • Reliability is consistency. Internal reliability is consistency within a measure (checked by split-half); external reliability is consistency over time (checked by test-retest); inter-rater reliability is agreement between observers (checked by correlating their records).
  • Validity is accuracy. Internal validity is whether the IV (not a confound) caused the change; ecological validity is whether findings apply outside the study setting; population validity is whether they generalise beyond the sample.

Levels of measurement and presenting data

Examples in context

Example 1. Why stratified sampling improves a school study. Imagine surveying exam stress across a school of 1,000 students split 60 per cent lower school and 40 per cent upper school. A stratified sample of 100 would take 60 lower-school and 40 upper-school students (often selected randomly within each stratum), so the proportions match the population. This guards against an opportunity sample that, say, only caught upper-school students in the library and therefore over-represented older, possibly more stressed, students.

Example 2. An ethics cost-benefit judgement. A study on the effects of being ignored might cause mild distress, so a researcher weighs that cost against the benefit of understanding social exclusion. Protections include full informed consent where possible (or presumptive consent), a clear right to withdraw, monitoring for distress, and a thorough debrief. If the likely harm outweighs the scientific value, the study should be redesigned or abandoned. Showing this reasoning is exactly the evaluation OCR rewards in ethics questions.

Try this

Q1. Explain one strength of stratified sampling. [2 marks]

  • Cue. It is highly representative because subgroups appear in proportion to the population, so findings generalise well.

Q2. Identify the level of measurement of scores on a 1 to 5 satisfaction rating scale. [1 mark]

  • Cue. Ordinal, because the scores are ranked but the intervals between points are not necessarily equal.

Q3. Describe one way a researcher could improve the reliability of a questionnaire. [3 marks]

  • Cue. Use a test-retest method: give the same questionnaire to the same people on two occasions and correlate the scores; a strong positive correlation shows external reliability.

Exam-style practice questions

Practice questions written in the style of OCR exam questions on this dot point, with worked answer explainers. The year tag is the paper they imitate, not the source.

OCR 20184 marksA researcher selects every tenth name from an alphabetical staff list of 200 employees. Identify the sampling method and explain one strength and one weakness of using it here. [4 marks]
Show worked answer →

An application item: name the method from the stem, then evaluate (AO2 and AO3).

Method: systematic sampling, because participants are chosen at a fixed interval (every tenth name) from the list.

Strength: it is objective and avoids researcher bias in selection, because the interval is fixed in advance and the researcher cannot favour particular people.

Weakness: it is not truly random and could coincide with a pattern in the list (for example, if every tenth entry happened to be a department head), reducing representativeness.

Markers reward correctly identifying systematic sampling, a strength tied to objectivity or lack of bias, and a weakness tied to a hidden periodic pattern or imperfect representativeness.

OCR 20226 marksExplain what is meant by reliability and validity, and describe one way a researcher could check the reliability of an observation. [6 marks]
Show worked answer →

Tests two core concepts plus a method (AO1 and AO2).

Reliability is consistency: a measure is reliable if it produces the same results when repeated under the same conditions. Validity is accuracy: a measure is valid if it measures what it claims to measure.

Checking reliability of an observation: use inter-rater reliability. Two observers independently code the same behaviour using the same behavioural categories, then their records are correlated (for example with Spearman's rho); a strong positive correlation (commonly +0.8+0.8 or above) shows the coding is consistent between observers.

Markers reward a clear distinction between consistency (reliability) and accuracy (validity), and a correct description of inter-rater reliability with the idea of correlating two observers' records.

Related dot points

Sources & how we know this