Quantitative and qualitative data | AQA A-Level Psychology Revision

For 7182 specification, first teach in September 2025

AQA A-Level Psychology | Free Revision Notes

Estimated study time: 55 minutes

Psychological researchers can record information as numbers or as detailed descriptions. This Quantitative and qualitative data A-Level Psychology revision page explains the distinction between these two forms of data, how each may be collected and why the method used does not always determine the type of data produced. You will also evaluate the usefulness of numerical and non-numerical evidence. Understanding this distinction is essential before studying descriptive statistics, graphs, levels of measurement and inferential testing.

Learning Objectives 🎯

By the end of this revision page, you should be able to:

• Define quantitative and qualitative data.

• Distinguish numerical data from non-numerical data.

• Distinguish a type of data from a data collection technique.

• Identify the type of data produced in unfamiliar investigations.

• Explain how the same research method may produce different types of data.

• Evaluate the strengths and limitations of quantitative and qualitative data.

• Suggest an appropriate type of data for a psychological investigation.

Revision Notes 📚

What is psychological data?

Data are the information collected during an investigation.

Psychologists use data to:

• Describe behaviour.

• Compare participants or conditions.

• Examine relationships between variables.

• Test hypotheses.

• Evaluate theories.

• Draw conclusions about a research aim.

Data may take many forms, including:

• Test scores.

• Response times.

• Frequencies of behaviour.

• Questionnaire ratings.

• Written answers.

• Interview responses.

• Descriptions of observed behaviour.

• Material collected from existing documents or recordings.

These examples can be organised into two broad types:

1. Quantitative data

2. Qualitative data

The distinction concerns the form of the information collected, not simply the name of the research method.

Quantitative data

Quantitative data are numerical data.

They express behaviour, responses or characteristics using numbers.

Examples include:

• The number of words recalled.

• The time taken to complete a task.

• A score on a psychological test.

• The frequency of aggressive behaviour.

• A rating selected on a numerical scale.

• The number of correct questionnaire answers.

• The number of minutes spent revising.

• The number of participants choosing each response.

Quantitative data allow psychologists to count, measure and compare outcomes.

Examples of quantitative data

Research question	Possible quantitative data
Does background noise affect concentration?	Number of correct responses on a concentration task
Is sleep related to memory?	Hours of sleep and number of words recalled
How frequently does helping behaviour occur?	Number of helping behaviours recorded
How confident are students about an examination?	Rating from 1 to 10
Does task condition affect performance speed?	Completion time measured in seconds

Each example produces a numerical value that can be analysed.

Quantitative data and operationalisation

Psychological concepts must be defined clearly before they can be measured numerically.

For example, a researcher cannot simply record “memory”. Memory might be operationalised as:

The number of words correctly recalled from a list of 20 within two minutes.

This produces a numerical score between 0 and 20.

Similarly, concentration might be operationalised as:

The number of targets correctly identified during a five-minute visual-search task.

The quality of quantitative data therefore depends on defining psychological variables precisely.

A numerical measure is not automatically a good measure. The researcher must still consider whether it represents the psychological concept appropriately.

Sources of quantitative data

Quantitative data may be collected through several research methods.

Experiments

Experiments often produce measurements of the dependent variable, such as:

• Number of correct answers.

• Test score.

• Response time.

• Frequency of an action.

• Rating of an experience.

For example, participants in two conditions might receive scores on the same memory task.

Observations

Researchers may count the number of times a behavioural category occurs.

For example:

• Number of interruptions.

• Number of helping behaviours.

• Number of times a participant leaves their seat.

• Frequency of verbal aggression.

An observation can therefore produce quantitative frequency data.

Questionnaires

Closed questions can produce numerical data.

For example:

How confident are you about your next examination?

Participants might select a rating from 1 to 10.

The answers can then be counted, compared or summarised.

Interviews

A structured interview may use closed questions with fixed response options.

For example:

How many hours did you revise yesterday?

The answer produces quantitative data even though it was collected during an interview.

Correlations

A correlation requires numerical measurements of two co-variables.

For example:

• Number of hours slept.

• Score on a concentration test.

The two sets of numerical data can be examined for a relationship.

Content analysis

Researchers may place material into coding categories and count how often each category occurs.

For example, a researcher could count the number of aggressive acts shown in a series of television programmes.

Analysing quantitative data

Quantitative data can be summarised using numerical techniques.

Researchers may calculate:

• Mean.

• Median.

• Mode.

• Range.

• Standard deviation.

• Percentages.

• Correlation coefficients.

The most appropriate calculation depends partly on the data and the research question.

These techniques are introduced in summarising data using typical scores and measuring variation within a data set.

Quantitative data may also be displayed using:

• Tables.

• Bar charts.

• Histograms.

• Scattergrams.

The chosen display should represent the data accurately and make the main pattern easy to understand.

Qualitative data

Qualitative data are non-numerical data that usually take the form of words, descriptions or detailed accounts.

Examples include:

• A participant’s description of an experience.

• A written response to an open question.

• An interview transcript.

• Detailed notes about observed behaviour.

• A personal account included in a case study.

• Descriptions of themes found in documents or recordings.

Qualitative data can provide information about:

• Thoughts.

• Feelings.

• Meanings.

• Experiences.

• Explanations.

• Reasons for behaviour.

• The context in which behaviour occurs.

Examples of qualitative data

Research question	Possible qualitative data
How do students experience examination stress?	Detailed interview accounts
Why do employees find a task difficult?	Written explanations in response to an open question
How do participants respond during a group activity?	Descriptive observational notes
What do people think about working from home?	Open-ended questionnaire responses
How does an individual describe a significant experience?	Detailed case-study material

These responses cannot initially be represented simply by a numerical score without some form of coding or categorisation.

Sources of qualitative data

Qualitative data may also be collected using several methods.

Open questionnaire questions

An open question allows participants to answer in their own words.

For example:

Explain how you feel when preparing for an important examination.

Participants may describe different experiences, concerns and coping strategies.

Interviews

An unstructured interview allows the interviewer to explore participants’ responses in depth.

Participants may:

• Explain their experiences.

• Provide examples.

• Clarify what they mean.

• Introduce information the researcher had not predicted.

The resulting material may be recorded as notes, written transcripts or audio recordings.

Observations

An observer may write detailed descriptions of behaviour rather than only recording frequencies.

For example:

The participant moved away from the group, watched the other participants for approximately one minute and then returned after being invited to join the task.

This provides contextual information that would be lost if the observer recorded only “left group: one occurrence”.

Case studies

Case studies may include:

• Interview accounts.

• Personal documents.

• Descriptions of behaviour.

• Detailed life histories.

• Observations collected over time.

These sources can provide a detailed account of an individual, group or event.

Content analysis

A content analysis may begin with non-numerical material such as:

• Newspaper articles.

• Interview transcripts.

• Social media posts.

• Television programmes.

• Written documents.

Researchers may describe themes qualitatively or code the material into categories and count it quantitatively.

Data type and data collection technique

A data type is the form of the information produced.

A data collection technique is the procedure used to obtain that information.

This distinction is essential.

• Quantitative and qualitative describe data.

• Questionnaires, interviews, observations and experiments describe ways of collecting data.

The same collection technique may produce either type.

Questionnaire example

A questionnaire may contain a closed question:

How many hours did you revise last weekend?

The response is quantitative because it produces a number.

The same questionnaire may also contain an open question:

Explain what affected the amount of revision you completed.

The response is qualitative because the participant answers in their own words.

The questionnaire is the collection technique. The form of each answer determines the data type.

You can review how question format affects responses in constructing open and closed questions.

Interview example

A structured interview might ask:

On how many days during the past week did you feel stressed?

This produces quantitative data.

An unstructured interview might ask:

Tell me about your experiences of stress during the past week.

This produces qualitative data.

Both responses were collected through an interview, but they are different types of data.

The distinction between interview formats is explored in structured and unstructured interviews.

Observation example

An observer may use an observation schedule to record:

Behaviour	Frequency
Shares materials	6
Gives task-related information	4
Interrupts another participant	3

These are quantitative data.

Alternatively, the observer may write:

The participant initially worked alone but began sharing materials after another group member asked for help.

This is qualitative data.

The observation technique does not, by itself, determine the form of the evidence.

Experiment example

An experiment often produces quantitative measurements, but this is not a requirement of the method itself.

A researcher investigating task difficulty might collect:

• Quantitative data: number of items completed correctly.

• Qualitative data: participants’ descriptions of which parts they found difficult.

The experiment concerns manipulation or comparison of variables. The numerical or descriptive form of the responses determines the data type.

Correlation example

A correlation is normally based on quantitative measurements because researchers calculate the relationship between two co-variables.

For example:

• Hours spent revising.

• Test score.

However, the questionnaire or interview used to obtain those measurements could also collect additional qualitative responses.

The correlation uses the numerical data, while the wider investigation may contain both forms.

Data type is not the same as research method

Research method or technique	Possible quantitative data	Possible qualitative data
Experiment	Scores, times, frequencies or ratings	Participant descriptions of the task
Observation	Behavioural frequencies or durations	Detailed field notes
Questionnaire	Closed-question scores or ratings	Open written responses
Interview	Numerical answers to fixed questions	Detailed verbal accounts
Content analysis	Frequencies within coding categories	Descriptions of themes
Case study	Test scores or numerical records	Interviews, observations and personal accounts
Correlation	Measurements of two co-variables	Additional explanations gathered alongside the measurements

This table shows why it is inaccurate to state that questionnaires always produce quantitative data or that interviews always produce qualitative data.

Data type is not the same as data source

Quantitative and qualitative data describe the form of the information.

Primary and secondary data describe where the information came from.

A data set can therefore be:

• Primary and quantitative.

• Primary and qualitative.

• Secondary and quantitative.

• Secondary and qualitative.

For example:

Example	Data type	Data source
Test scores collected by the researcher	Quantitative	Primary
Interview accounts collected by the researcher	Qualitative	Primary
Official numerical records collected by another organisation	Quantitative	Secondary
Existing diary entries analysed by a psychologist	Qualitative	Secondary

This distinction is developed in comparing original and previously collected evidence.

Evaluating quantitative data

Strength: easier comparison

Quantitative data allow researchers to compare:

• Participants.

• Conditions.

• Groups.

• Time periods.

• Scores on different variables.

For example, a researcher can compare the mean memory score of a silent condition with the mean score of a noise condition.

A clear numerical difference may be easier to identify than a large collection of written descriptions.

Strength: statistical analysis

Numerical data can be analysed using descriptive and inferential statistics.

Researchers can:

• Summarise typical scores.

• Measure variation.

• Examine relationships.

• Assess statistical significance.

• Present patterns in graphs and tables.

This makes quantitative data especially useful when the research aim concerns the size, frequency or distribution of an effect.

Strength: concise presentation

A large number of numerical scores can be summarised using:

• A mean or median.

• A measure of dispersion.

• A percentage.

• A table.

• A graph.

This allows readers to understand the overall pattern without examining every individual score.

For example, the scores of 100 participants may be summarised using a mean and standard deviation.

Strength: potentially greater objectivity

Quantitative measures may reduce personal interpretation when they are operationalised and scored clearly.

For example:

Number of words correctly recalled

requires less judgement than:

How good the participant’s memory appeared to be.

Objective scoring rules may improve consistency between researchers.

However, numerical data are not automatically objective. A poorly designed rating scale or subjective coding system can still be influenced by researcher judgement.

Strength: easier replication

A numerical measurement can often be repeated consistently when the procedure is clearly described.

For example, another researcher could use:

• The same test.

• The same time limit.

• The same scoring criteria.

• The same numerical scale.

This may support reliability and replication.

Limitation: reduced detail

A numerical score may show what happened without explaining why it happened.

For example, a participant may give an examination-confidence rating of 3 out of 10.

The number does not explain:

• Why confidence is low.

• Which part of the examination causes concern.

• Whether confidence changes across subjects.

• What experiences influenced the rating.

Qualitative data may be needed to understand the meaning behind the score.

Limitation: complex experiences may be oversimplified

Psychological experiences can be difficult to represent using one numerical value.

For example, stress may involve:

• Thoughts.

• Emotions.

• Physical responses.

• Behaviour.

• Social circumstances.

Reducing this experience to a single score may leave out important information.

The measure may be easy to analyse but provide an incomplete account of the participant’s experience.

Limitation: numbers can create a misleading appearance of precision

A numerical result can appear exact even when the underlying measure is weak.

For example, a participant gives a stress rating of 7 out of 10. This looks precise, but different participants may interpret “7” differently.

Researchers should not assume that a number guarantees:

• Objectivity.

• Reliability.

• Validity.

• Accurate measurement.

The quality of the operational definition and scale must still be evaluated.

Limitation: predetermined categories may restrict responses

Closed questions and rating scales limit participants to the response options selected by the researcher.

For example:

How helpful was the programme?

• Very helpful

• Helpful

• Unhelpful

• Very unhelpful

A participant may have found one part helpful and another part unhelpful. The fixed choices may not allow this complexity to be expressed.

Limitation: unexpected information may be missed

Quantitative measures focus on variables chosen before data collection.

Participants cannot easily introduce new concerns or explanations that the researcher did not anticipate.

This may limit the development of new ideas.

Evaluating qualitative data

Strength: rich and detailed information

Qualitative data allow participants to provide detailed accounts in their own words.

They may explain:

• What happened.

• How they interpreted it.

• Why they responded as they did.

• Which parts of an experience were important.

• How different factors were connected.

This can produce a fuller account than a numerical score alone.

Strength: greater context

Qualitative data can preserve the context in which behaviour occurs.

For example, an observational frequency may show that a participant left a group three times.

Detailed notes might reveal that:

• The participant left to collect materials.

• They were asked to leave by another person.

• They returned and helped complete the task.

The contextual account may change how the behaviour is interpreted.

Strength: participants can express their own meanings

Open questions and flexible interviews do not force every participant into the same fixed response categories.

Participants can:

• Explain what matters to them.

• Clarify unusual experiences.

• Challenge assumptions within the question.

• Introduce information the researcher did not predict.

This may improve the validity of the account where the research aim concerns personal experiences or meanings.

Strength: useful for exploring unfamiliar topics

When researchers do not yet know which responses are likely, open-ended data can reveal:

• New themes.

• Unexpected explanations.

• Important variables.

• Differences between participants.

These findings may help researchers develop future:

• Questions.

• Measures.

• Hypotheses.

• Investigations.

Strength: can explain numerical patterns

Qualitative responses may help researchers understand quantitative findings.

For example, a questionnaire may show that students with lower confidence revise less frequently.

Interviews might reveal several different explanations:

• Fear of failure.

• Lack of time.

• Uncertainty about revision methods.

• Belief that revision will not help.

The numerical relationship identifies a pattern, while the qualitative accounts provide possible explanations.

Limitation: difficult and time-consuming to analyse

Large amounts of written or spoken material may require:

• Transcription.

• Repeated reading.

• Development of categories or themes.

• Careful coding.

• Comparison between researchers.

This may take much longer than calculating summary statistics from numerical scores.

Limitation: researcher interpretation

Qualitative analysis often requires the researcher to decide:

• Which material is important.

• How responses should be categorised.

• What a statement means.

• Which quotations represent a theme.

• How themes are connected.

Researcher expectations may influence these judgements.

Clear coding procedures, investigator training and comparison between researchers may reduce this influence.

Limitation: lower reliability may occur

Participants may give different answers when:

• Questions are phrased differently.

• Interviewers use different prompts.

• The order of questions changes.

• The researcher interprets responses differently.

• Coding categories are unclear.

Flexible qualitative procedures can be difficult to repeat in exactly the same way.

This does not mean that qualitative data are always unreliable. Reliability depends on how carefully the procedure and analysis are designed.

Limitation: difficult to summarise

Detailed responses cannot always be reduced to a simple average or percentage without losing meaning.

This may make it harder to:

• Compare large groups.

• Identify an overall pattern.

• Present the findings concisely.

• Conduct some forms of statistical analysis.

Limitation: a small number of accounts may not represent everyone

Qualitative investigations may collect very detailed information from a relatively small number of participants.

These accounts can be valuable, but researchers should be cautious when applying them to a wider population.

However, generalisation depends on the sample and method, not simply on whether the data are qualitative.

Limitation: participants may not provide accurate accounts

Detailed verbal data do not automatically give direct access to a participant’s true thoughts or experiences.

Participants may:

• Forget details.

• Misunderstand questions.

• Alter responses because of demand characteristics.

• Present themselves favourably.

• Struggle to express an experience in words.

Researchers must still evaluate the validity of the evidence.

Comparing quantitative and qualitative data

Feature	Quantitative data	Qualitative data
Form	Numerical	Non-numerical, usually words or descriptions
Example	Number of correct answers	Explanation of how the task felt
Main purpose	Measuring, counting and comparing	Exploring meanings, experiences and context
Typical analysis	Statistics, tables and graphs	Categories, themes and detailed interpretation
Main strength	Easier comparison and statistical analysis	Richness and depth
Main limitation	May oversimplify experience	May be difficult and subjective to analyse
Researcher control	Responses are often more restricted	Participants may answer more freely
Replication	Often easier with standardised measures	May be harder with flexible procedures
Unexpected findings	Less likely with fixed measures	More likely to emerge
Presentation	Concise numerical summaries	Detailed written accounts

Neither type is always superior. The most appropriate choice depends on the research aim.

Choosing quantitative data

Quantitative data may be most useful when the researcher wants to:

• Measure how much of something occurs.

• Compare two or more conditions.

• Calculate an average.

• Examine the strength of a relationship.

• Test a hypothesis statistically.

• Present a clear numerical pattern.

• Collect standardised data from many participants.

For example, a psychologist investigating whether noise affects performance may need the number of correct answers from each condition.

Choosing qualitative data

Qualitative data may be most useful when the researcher wants to:

• Explore personal experiences.

• Understand reasons for behaviour.

• Examine how participants interpret an event.

• Study a topic in depth.

• Identify unexpected themes.

• Preserve social or situational context.

• Develop ideas for future research.

For example, a psychologist investigating students’ experiences of examination pressure may need detailed interview accounts.

Matching the data to the aim

Consider these two aims:

Aim 1

To investigate whether students who sleep for eight hours obtain higher memory scores than students who sleep for four hours.

Quantitative data are appropriate because the researcher needs numerical memory scores that can be compared.

Aim 2

To explore how students describe the effect of poor sleep on their learning.

Qualitative data are appropriate because the aim concerns participants’ detailed experiences and explanations.

The research question should guide the choice of data rather than the researcher choosing a preferred data type first.

Collecting both types of data

An investigation may collect both quantitative and qualitative data.

For example, a questionnaire about revision may include:

1. How many hours did you revise last week?

2. Rate your confidence from 1 to 10.

3. Explain which factors affected your revision.

Questions one and two produce quantitative data. Question three produces qualitative data.

Using both forms may provide:

• A numerical pattern.

• Detailed explanations of that pattern.

• Evidence about differences between participants.

• Information the researcher did not predict.

However, collecting both types may also increase:

• The time required.

• The complexity of analysis.

• The length of the investigation.

• The difficulty of presenting a clear conclusion.

Quantitative and qualitative data in observations

A researcher investigates social behaviour during a group task.

Quantitative recording

The observer counts:

• Frequency of sharing.

• Frequency of interruptions.

• Number of questions asked.

• Time spent working alone.

This allows numerical comparison.

Qualitative recording

The observer writes:

One participant initially ignored the group’s suggestions, but began sharing information after another participant asked for their opinion.

This provides context and detail.

The researcher must decide whether the aim concerns frequency, meaning or both. This decision should be made while planning categories and sampling procedures.

Quantitative and qualitative data in content analysis

A researcher analyses newspaper articles about psychological research.

Quantitative approach

The researcher could count:

• How often positive language appears.

• How many articles mention limitations.

• The number of times particular topics occur.

Qualitative approach

The researcher could describe:

• The main themes.

• How psychologists are represented.

• The type of language used.

• Differences in how findings are explained.

Material may also be coded into categories and converted into numerical frequencies. This will be developed in coding written, visual or spoken material.

Converting qualitative data into quantitative data

Researchers may convert qualitative material into numbers by:

1. Reading or observing the material.

2. Constructing coding categories.

3. Defining each category clearly.

4. Assigning parts of the material to categories.

5. Counting the frequency of each category.

For example, interview responses about revision could be coded as:

• Lack of time.

• Low motivation.

• Uncertainty about methods.

• Competing responsibilities.

The researcher could then count how many participants mentioned each theme.

This makes numerical comparison possible, but some detail may be lost when complex responses are reduced to categories.

Coding must be clear

Coding categories should be:

• Relevant to the research aim.

• Operationalised.

• Distinct.

• Applied consistently.

• Capable of representing the original material.

If categories overlap or require excessive interpretation, different researchers may code the same statement differently.

For example, the statement:

“I kept putting revision off because I did not know where to start.”

could potentially be coded as:

• Low motivation.

• Uncertainty about revision methods.

• Avoidance.

The researcher must establish clear coding rules.

Data type and levels of measurement

Quantitative data can be organised according to their level of measurement:

• Nominal.

• Ordinal.

• Interval.

The level of measurement affects:

• Which descriptive statistics are appropriate.

• How data may be displayed.

• Which inferential test may be selected.

For example, numbers used merely as category labels do not provide the same type of measurement as numerical scores with equal units.

This distinction is studied fully in nominal, ordinal and interval data.

Quantitative data do not always provide interval measurement

Students sometimes assume that all numbers are interval data.

This is incorrect.

For example, participants may select:

1. Strongly disagree

2. Disagree

3. Agree

4. Strongly agree

The numerical labels show an order, but the gap between responses cannot automatically be assumed to be equal.

The values are numerical, so the data are quantitative, but the level of measurement still needs to be identified separately.

Qualitative data and coding

Qualitative data may be converted into nominal quantitative data through coding.

For example, interview responses could be categorised as:

• Positive experience.

• Negative experience.

• Mixed experience.

The original responses are qualitative. The category frequencies are quantitative.

Researchers should explain clearly whether they are discussing:

• The original verbal material.

• The coded categories.

• The numerical frequency of each category.

Data quality and validity

Qualitative data are sometimes described as more valid because they provide depth and context.

This may be true in some investigations, but it should not be treated as a universal rule.

A qualitative response may have low validity if:

• The question is leading.

• The participant misunderstands it.

• Demand characteristics influence the response.

• The interviewer affects the answer.

• The researcher misinterprets the account.

Similarly, quantitative data may have good validity if the measure represents the intended concept accurately.

Validity depends on the quality of the research procedure and measurement, not simply on whether the information is numerical or verbal.

Data quality and reliability

Quantitative data are sometimes described as more reliable because they use standardised measurements.

This may be true when:

• Instructions are consistent.

• The measure is operationalised clearly.

• Scoring is objective.

• The equipment is dependable.

However, numerical data may still be unreliable if the measure produces inconsistent results.

Qualitative data may also be collected reliably when:

• Interview procedures are carefully planned.

• Questions and prompts are consistent.

• Coding categories are clear.

• Researchers are trained.

• Agreement between coders is checked.

The relationship between consistency and data collection is examined in reliability across psychological methods.

Data and objectivity

Quantitative data can reduce some forms of researcher judgement, but numbers do not remove interpretation entirely.

Researchers still decide:

• Which variables to measure.

• How to operationalise them.

• Which scores to include.

• Which analysis to conduct.

• How to interpret the result.

Qualitative data require interpretation more visibly, particularly when developing themes or categories.

In both cases, researchers should:

• Explain their procedures.

• Apply rules consistently.

• Report unexpected findings.

• Avoid selecting only evidence that supports their expectations.

Data and demand characteristics

Both types of data may be affected by demand characteristics.

Quantitative example

A participant guesses that the researcher expects lower concentration in the noise condition and deliberately works more slowly.

The response time is numerical, but it has still been influenced by the participant’s expectations.

Qualitative example

A participant gives an answer they believe will please an interviewer.

The detailed response may not accurately represent their genuine view.

The data format does not protect an investigation from participant reactivity.

Data and investigator effects

Both types may also be affected by investigator effects.

Quantitative example

A researcher scores an ambiguous response as correct for one condition but incorrect for another.

Qualitative example

An interviewer asks more detailed follow-up questions when participants give answers that support the expected conclusion.

Standardisation, objective scoring and investigator training may reduce these influences.

Presenting quantitative data

Quantitative findings should be presented using appropriate numerical summaries and displays.

Researchers should:

• Label tables and graphs clearly.

• Use suitable units.

• Report calculations accurately.

• Avoid misleading scales.

• Select a display suited to the data.

• Explain what the numerical pattern shows.

These decisions are developed in constructing and interpreting data displays.

Presenting qualitative data

Qualitative findings may be presented through:

• Written summaries.

• Categories.

• Themes.

• Carefully selected examples.

• Extracts that illustrate a pattern.

Researchers should avoid selecting only responses that support their preferred interpretation.

The report should explain:

• How the themes were identified.

• How material was coded.

• Whether more than one researcher analysed the data.

• How disagreements were handled.

• How the examples relate to the wider data set.

Reporting quantitative and qualitative investigations

A scientific report should make the data type and analysis clear.

For quantitative data

The report should explain:

• What numerical measure was collected.

• How it was scored.

• Which descriptive statistics were used.

• How the data were displayed.

• Whether inferential testing was conducted.

For qualitative data

The report should explain:

• How verbal or descriptive material was recorded.

• How categories or themes were created.

• How interpretation was conducted.

• How consistency between researchers was checked.

• How findings were supported using the collected material.

These details belong within the method, results and discussion of a report.

Worked example: student revision questionnaire

A psychologist investigates students’ revision experiences.

The questionnaire contains four items.

Item 1

How many hours did you revise during the past seven days?

Data produced: Quantitative

The response is numerical and can be compared across participants.

Item 2

Rate your confidence about your next examination from 1 to 10.

Data produced: Quantitative

The response is represented by a number on a scale.

Item 3

Which revision resource did you use most often?

• Textbook

• Revision website

• Flashcards

• Practice papers

Data produced: Quantitative after responses are counted

The options are categories. The researcher can count the number of participants selecting each one.

Item 4

Explain why you preferred this revision resource.

Data produced: Qualitative

Participants answer in their own words and may provide detailed explanations.

Evaluation of the questionnaire

The quantitative responses allow the researcher to:

• Calculate frequencies.

• Compare confidence ratings.

• Identify patterns.

• Present results in tables or graphs.

The qualitative responses allow the researcher to:

• Understand participants’ preferences.

• Identify unexpected reasons.

• Preserve individual explanations.

However, the open responses may take longer to code and may be interpreted differently by different researchers.

Worked example: classroom observation

A psychologist investigates engagement during independent work.

Quantitative approach

The observer records every occasion on which a participant:

• Writes on the task sheet.

• Asks a task-related question.

• Looks away from the task for more than five seconds.

• Leaves their seat.

This produces frequencies that can be compared.

Qualitative approach

The observer writes detailed notes about:

• The sequence of behaviour.

• Interactions with classmates.

• Changes in engagement.

• Events occurring before off-task behaviour.

This provides more context.

Evaluation

Quantitative recording may be:

• Easier to summarise.

• More objective where categories are clear.

• Suitable for comparing participants.

However, it may fail to explain why behaviour occurred.

Qualitative recording may:

• Reveal contextual influences.

• Describe complex behaviour.

• Identify unexpected patterns.

However, it may require greater interpretation and be harder to record while several behaviours occur at once.

Choosing the most useful type of data

A researcher should ask:

1. What is the exact research aim?

2. Is the researcher interested in amount, frequency or difference?

3. Is the researcher interested in meaning, experience or explanation?

4. Does the hypothesis require numerical comparison?

5. How many participants will be studied?

6. How much time is available for analysis?

7. Can the intended concept be measured validly using numbers?

8. Will fixed response options omit important information?

9. How will reliability be checked?

10. How will the data be reported?

The chosen data should help answer the research question rather than merely being convenient to collect.

Quantitative and qualitative data A-Level Psychology revision: exam application

Examination questions may ask you to:

• Identify the type of data.

• Explain the distinction between a data type and a collection technique.

• Construct a question producing a particular type of data.

• Evaluate quantitative or qualitative evidence.

• Suggest which type would be appropriate for an investigation.

• Explain how qualitative material could be coded.

• Apply the distinction to a table, questionnaire or interview.

Identifying quantitative data

Look for:

• Counts.

• Scores.

• Times.

• Ratings.

• Frequencies.

• Numerical measurements.

Example:

Participants recorded how many hours they slept.

This produces quantitative data.

Identifying qualitative data

Look for:

• Words.

• Descriptions.

• Explanations.

• Personal accounts.

• Open responses.

• Interview transcripts.

Example:

Participants described how lack of sleep affected them.

This produces qualitative data.

Explaining the data collection distinction

Weak answer:

Questionnaires are quantitative and interviews are qualitative.

This is incorrect because either technique may produce either type of data.

Stronger answer:

Quantitative and qualitative describe the form of the information collected. Questionnaires and interviews are collection techniques. A questionnaire may produce numerical ratings through closed questions and detailed verbal data through open questions.

Constructing a quantitative question

A suitable question should produce a numerical or countable answer.

Example:

How many hours did you revise during the past seven days?

The time period is clearly defined and the answer can be recorded numerically.

Constructing a qualitative question

A suitable question should allow the participant to answer in their own words.

Example:

Explain which factors affected your revision during the past seven days.

This encourages a detailed response rather than restricting participants to prepared choices.

Evaluating data in context

Avoid giving a generic point without applying it.

Weak answer:

Qualitative data are detailed.

Stronger answer:

Asking students to describe their examination anxiety in their own words may reveal which parts of the examination they find stressful, providing more detail than a single anxiety rating.

Weak answer:

Quantitative data are easy to analyse.

Stronger answer:

Numerical anxiety ratings could be used to calculate an average and compare two groups, making the overall difference easier to identify.

Key Words 🔑

Key word	Student-friendly definition	How it may be used in an exam
Data	Information collected during a psychological investigation.	Identify what evidence a researcher has recorded.
Quantitative data	Numerical information that can be counted or measured.	Identify scores, ratings, times or frequencies.
Qualitative data	Non-numerical information, usually expressed through words or descriptions.	Identify open responses, interview accounts or descriptive notes.
Data type	The form in which collected information is recorded.	Distinguish quantitative and qualitative information.
Data collection technique	The procedure used to obtain information from participants or other sources.	Distinguish a questionnaire, interview or observation from the data it produces.
Closed question	A question with fixed response options.	Construct a question likely to produce quantitative data.
Open question	A question allowing participants to respond in their own words.	Construct a question likely to produce qualitative data.
Numerical data	Information represented using numbers.	Recognise quantitative evidence.
Descriptive data	Detailed information expressed in words.	Recognise qualitative evidence.
Coding	Placing material into defined categories for analysis.	Explain how qualitative material may be converted into frequencies.
Category	A defined group into which information or behaviour is placed.	Explain how content or responses may be organised.
Frequency	The number of times a response or behaviour occurs.	Identify a quantitative measure in an observation or content analysis.
Objectivity	Basing decisions on clear evidence rather than personal opinion.	Evaluate whether numerical scoring or coding reduces interpretation.
Reliability	The consistency of a procedure or measurement.	Evaluate whether data would be recorded similarly on another occasion.
Validity	The extent to which research measures what it intends to measure.	Evaluate whether a numerical or verbal measure represents the intended concept.
Theme	A recurring idea or pattern identified in qualitative material.	Explain how interview or written data may be organised.

Common Mistakes ⚠️

Mistake: Defining quantitative data as data collected through an experiment.

Why this is incorrect:Quantitative describes numerical information, not the method used to collect it.

How to improve:Identify whether the actual responses, scores or observations are represented numerically.

Mistake: Saying that interviews always produce qualitative data.

Why this is incorrect:An interview may use closed questions that produce numbers, frequencies or fixed-choice responses.

How to improve:Examine the question format and the information recorded.

Mistake: Saying that questionnaires always produce quantitative data.

Why this is incorrect:Open questionnaire questions allow participants to give qualitative written responses.

How to improve:Distinguish the questionnaire as a technique from the form of its answers.

Mistake: Assuming that all observations produce quantitative data.

Why this is incorrect:Observers may record frequencies or write detailed descriptions of behaviour.

How to improve:Identify whether the observation produces counts or descriptive notes.

Mistake: Describing qualitative data as inaccurate.

Why this is incorrect:Qualitative data can provide detailed and meaningful evidence. Its quality depends on the procedure, questions and analysis.

How to improve:Evaluate the particular investigation rather than dismissing the entire data type.

Mistake: Claiming that quantitative data are automatically objective.

Why this is incorrect:Researchers still decide how variables are measured and how scores are interpreted.

How to improve:Explain that clear operationalisation and scoring may increase objectivity.

Mistake: Claiming that qualitative data are always more valid.

Why this is incorrect:Detailed responses may still be influenced by unclear questions, demand characteristics or investigator interpretation.

How to improve:Explain why the data may be valid in the specific context and identify any threats.

Mistake: Treating numerical labels as proof of interval measurement.

Why this is incorrect:Numbers may represent ordered categories without equal intervals.

How to improve:Identify the data type and level of measurement separately.

Mistake: Confusing qualitative data with secondary data.

Why this is incorrect:Qualitative describes the form of information. Secondary describes information originally collected by someone else.

How to improve:Identify both the data type and data source.

Mistake: Giving a generic evaluation without using the scenario.

Why this is incorrect:Application questions require an explanation of how the type of data affects that particular investigation.

How to improve:Refer to the exact score, question, behaviour or experience being investigated.

Exam-Style Questions ✍️

Question 1

Define quantitative data. (1 mark)

Question 2

Define qualitative data. (1 mark)

Question 3

A psychologist records the number of times each participant interrupts during a discussion.

Identify the type of data collected. (1 mark)

Question 4

Explain why a questionnaire should not automatically be described as a quantitative data collection technique. (2 marks)

Question 5

A researcher wants to investigate students’ experiences of examination stress.

Construct:

1. One question that would produce quantitative data.

2. One question that would produce qualitative data.

(4 marks)

Question 6

A psychologist interviews employees about working from home. Each employee gives a stress rating from 1 to 10 and then explains the reasons for their rating.

Identify the two types of data collected and explain how each could be useful. (4 marks)

Question 7

A researcher observes behaviour during a group task. The researcher records the frequency of helping behaviour but does not write any description of the circumstances in which it occurs.

Explain one strength and one limitation of collecting only quantitative data in this investigation. (4 marks)

Question 8

A psychologist asks participants an open question about their experience of a memory task.

Explain two strengths and two limitations of the qualitative data that may be produced. (6 marks)

Question 9

A researcher collects detailed interview responses about revision. The researcher then creates four categories and counts how many participants mention each one.

Explain how the investigation has used both qualitative and quantitative data. (4 marks)

Question 10

A college wants to investigate students’ use of revision resources.

Discuss the usefulness of quantitative and qualitative data for this investigation. In your answer, refer to:

• The types of information each could provide

• Methods of collecting each type

• Analysis and presentation

• Reliability

• Validity

• The possibility of collecting both types

(8 marks)