What research methods do psychologists use besides experiments, and how reliable and valid are they?
Non-experimental methods: observations, self-report (questionnaires and interviews), case studies and correlations, plus the concepts of reliability and validity used to evaluate all research.
A focused answer to the OCR GCSE Psychology J203 research methods topic on non-experimental methods, covering observations, questionnaires and interviews, case studies and correlations, and the concepts of reliability and validity used to evaluate all psychological research.
Reviewed by: AI editorial process; not yet individually human-reviewed
Have a quick question? Jump to the Q&A page
Jump to a section
What this dot point is asking
OCR wants you to explain the main non-experimental methods (observations, self-report through questionnaires and interviews, case studies and correlations) and the concepts of reliability and validity used to evaluate all research.
Non-experimental methods
- Observations: watching and recording behaviour, either in a natural setting (high ecological validity, less control) or a controlled setting. Strength: sees real behaviour. Weakness: observer bias and people may behave differently if they know they are watched.
- Self-report, questionnaires: written questions answered by many people. Strength: quick and gathers lots of data; Weakness: answers can be untruthful (social desirability) and closed questions lack depth.
- Self-report, interviews: asking questions in person, structured or unstructured. Strength: can gather rich, detailed data and follow up answers. Weakness: time-consuming and open to interviewer bias.
- Case studies: an in-depth study of one person or a small group, often using several methods. Strength: rich detail about rare cases. Weakness: cannot generalise from one case and relies on interpretation.
Correlations
- A positive correlation means both variables rise together (for example, more revision and higher marks).
- A negative correlation means as one rises, the other falls (for example, more screen time and less sleep).
- No correlation means there is no clear relationship.
Crucially, a correlation cannot show cause and effect, because a third variable could cause both, or the direction of the link is unknown. For example, ice cream sales and drowning correlate, but hot weather (a third variable) causes both.
Reliability and validity
These are different: a study can be reliable (consistent) without being valid (it might consistently measure the wrong thing).
- Improving reliability: standardise the procedure (same instructions, materials and conditions for everyone) so it can be repeated, and replicate the study to check the results are consistent.
- Improving validity: use a setting and task that reflect real life (ecological validity), control confounding variables (internal validity), and reduce demand characteristics.
Evaluating the methods
These methods matter because not every question can be answered by an experiment. Observations and case studies offer realism and depth but limited control and generalisation; questionnaires and interviews gather self-report data quickly or in depth but can be biased; correlations reveal relationships (useful when manipulation is impossible or unethical) but cannot prove cause. Judging every study on reliability (consistency) and validity (accuracy) is the key evaluation skill OCR rewards, and it connects directly to the design and control choices in planning research and sampling and variables.
Try this
Q1. What is the difference between a positive and a negative correlation? [2 marks]
- Cue. Positive: both variables rise together. Negative: as one rises, the other falls.
Q2. Why can a correlation not show cause and effect? [2 marks]
- Cue. A third variable could cause both, or the direction of the relationship is unknown.
Q3. Define reliability. [1 mark]
- Cue. Consistency: getting the same results when the study or measure is repeated under the same conditions.
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 20204 marksExplain what is meant by a correlation, and why a correlation cannot show cause and effect. (J203/02, Research methods)Show worked answer →
A 4-mark Explain item rewards a definition of correlation and the cause-and-effect point.
A correlation is a relationship between two co-variables, where as one changes the other tends to change too. A positive correlation means both rise together (for example, more revision and higher marks); a negative correlation means as one rises the other falls. However, a correlation cannot show cause and effect because a third variable could be responsible for both, or the direction of the link is unknown. For example, ice cream sales and drowning rates correlate, but neither causes the other; hot weather (a third variable) causes both. So correlation shows a relationship, not a cause.
Markers reward defining correlation (positive and negative co-variation) and explaining that it cannot show cause because of a possible third variable or unknown direction.
OCR 20215 marksExplain the difference between reliability and validity, and give one way of improving reliability. (J203/02, Research methods)Show worked answer →
A 5-mark Explain item rewards clear definitions of both and a way to improve reliability.
Reliability means consistency: a reliable measure or study gives the same results when repeated under the same conditions. Validity means accuracy or truthfulness: a valid study measures what it claims to measure and produces results that reflect real life. The two are different, because a study can be reliable (consistent) without being valid (it might consistently measure the wrong thing). One way to improve reliability is to standardise the procedure, using the same instructions, materials and conditions for every participant, so the study can be repeated and checked. Replicating the study and getting the same results also demonstrates reliability.
Markers reward defining reliability (consistency) and validity (measuring what is intended/reflecting real life), the point that they are distinct, and a way to improve reliability (standardisation or replication).
Related dot points
- Planning research: aims and hypotheses (directional and non-directional, the null hypothesis), experimental methods (laboratory, field and natural experiments), and experimental designs (independent measures, repeated measures and matched pairs).
A focused answer to the OCR GCSE Psychology J203 research methods topic on planning research, covering aims and hypotheses (directional, non-directional and null), the experimental methods (laboratory, field and natural experiments) and the experimental designs (independent measures, repeated measures and matched pairs).
- Sampling methods (random, opportunity, systematic, stratified) and variables: independent and dependent variables, operationalisation, extraneous and confounding variables, and controls.
A focused answer to the OCR GCSE Psychology J203 research methods topic on sampling and variables, covering sampling methods (random, opportunity, systematic and stratified), independent and dependent variables, operationalisation, extraneous and confounding variables, and controls.
- Types of data (quantitative and qualitative; primary and secondary) and descriptive statistics: measures of central tendency (mean, median, mode), the range, percentages and ratios, and ways of presenting data (tables, bar charts and scatter graphs).
A focused answer to the OCR GCSE Psychology J203 research methods topic on data and statistics, covering quantitative and qualitative data, primary and secondary data, the measures of central tendency (mean, median, mode), the range, percentages and ratios, and how to present data in tables, bar charts and scatter graphs.
- Ethical issues and guidelines in psychological research: informed consent, deception, the right to withdraw, protection from harm, confidentiality and debriefing, and how researchers deal with these issues.
A focused answer to the OCR GCSE Psychology J203 research methods topic on ethics, covering the key ethical issues and guidelines (informed consent, deception, the right to withdraw, protection from harm, confidentiality and debriefing) and how researchers deal with them.
Sources & how we know this
- OCR GCSE (9-1) Psychology J203 specification — OCR (2017)