Types of Data (AQA A-Level Psychology): Revision Notes
Types of Data
Introduction to data and analysis
When researchers conduct investigations, they gather raw information in various forms - words, numbers, images, or sounds. This raw material only becomes meaningful once context is added, transforming it into usable information. Data analysis represents the systematic process of converting this raw material into meaningful insights that can inform our understanding.
Qualitative and quantitative data
Qualitative data
Qualitative data consists of information presented in word form rather than numerical values. This type of data captures rich, descriptive accounts of participants' thoughts, feelings, and experiences. Examples include interview transcripts, diary extracts, counselling session notes, and observational records of behaviour.
Qualitative data collection methods focus on interpreting language and meaning. Researchers might gather this information through interviews or unstructured observations where the emphasis lies on understanding rather than measuring phenomena.
Common sources of qualitative data:
- Interview transcripts and recordings
- Diary entries and personal accounts
- Counselling or therapy session notes
- Observational field notes of behaviour
- Open-ended survey responses
Evaluation of qualitative data
Worked Example: Qualitative Data in Practice
A researcher studying stress in university students conducts in-depth interviews asking: "How do you experience stress during exam periods?"
Sample qualitative response: "I feel like my heart is constantly racing, and I can't concentrate on anything. It's like there's this heavy weight on my chest, and I keep thinking about all the things I haven't studied yet..."
This rich, descriptive data provides deep insights into the student's personal experience that numbers alone couldn't capture.
Strengths:
- Provides detailed, comprehensive insights that give researchers a deeper understanding of participants' perspectives
- Offers greater external validity as it captures authentic, real-world experiences
- Allows participants freedom to express their thoughts fully without being constrained by predetermined response categories
- Gives researchers access to the participant's genuine worldview and personal meaning-making
Limitations:
- Presents analysis challenges as it cannot be easily summarised through statistical methods, making pattern identification difficult
- Relies heavily on the researcher's subjective interpretation, which may introduce bias
- Conclusions may reflect the researcher's preconceptions rather than objective findings
- Time-consuming to analyse thoroughly due to the volume and complexity of textual data
Critical Point: While qualitative data provides rich insights, researchers must be aware of potential interpretation bias. The same data can be analysed differently by different researchers, potentially leading to varying conclusions.
Quantitative data
Quantitative data takes numerical form and can be counted, measured, and subjected to mathematical analysis. This includes scores from memory tests, reaction times, survey ratings, or frequency counts of specific behaviours. Such data lends itself readily to statistical analysis and can be converted into graphs, charts, and other visual representations.
Quantitative collection techniques typically gather individual numerical scores from participants, such as performance measures in controlled experiments.
Worked Example: Quantitative Data Collection
A researcher studying memory performance gives participants a word list to memorise, then tests recall after 24 hours.
Sample quantitative data:
- Participant 1: Recalled 12 out of 20 words (60%)
- Participant 2: Recalled 15 out of 20 words (75%)
- Participant 3: Recalled 8 out of 20 words (40%)
This numerical data can be easily analysed using statistical tests to determine average performance and compare between groups.
Evaluation of quantitative data
Strengths:
- Enables straightforward statistical analysis, allowing researchers to identify patterns and make comparisons between groups
- Provides more objective results as numerical data is less susceptible to researcher bias
- Facilitates clear comparisons and relationships between variables
- Produces findings that can be replicated and verified by other researchers
Limitations:
- Offers limited scope and depth compared to qualitative approaches
- May fail to capture the complexity of real-life experiences and behaviours
- Can oversimplify complex psychological phenomena by reducing them to numbers
- Lacks the rich contextual information that helps explain why patterns occur
Primary and secondary data
Primary data
Primary data (sometimes called field research) refers to original information collected directly by the researcher for their specific investigation. This first-hand data comes straight from participants through methods such as experiments, questionnaires, interviews, or observations conducted by the researcher themselves.
Primary data collection methods include:
- Controlled laboratory experiments
- Field experiments in natural settings
- Structured interviews and questionnaires
- Direct observation of behaviour
- Surveys designed for the specific research question
Evaluation of primary data
Strengths:
- Perfectly tailored to the research question as the researcher designs data collection specifically for their investigation
- Provides authentic, first-hand information directly from the source
- Allows researchers to control the quality and relevance of information gathered
- Enables questionnaires and interviews to target precisely the information needed
Limitations:
- Requires substantial time, effort, and resources from the researcher
- Demands considerable planning and preparation, particularly for experiments
- Can be expensive compared to accessing existing data sources
- May take weeks or months to collect sufficient data for analysis
Remember: Primary data collection requires careful ethical consideration, including obtaining informed consent and ensuring participant wellbeing throughout the research process.
Secondary data
Secondary data consists of information previously collected by other researchers or organisations, existing before the current investigation begins. This is sometimes called desk research as it often involves examining published sources rather than direct data collection.
Secondary data sources include journal articles, books, websites, government statistics (such as Census data), population records, and organisational databases like employee absence records.
Evaluation of secondary data
Strengths:
- Provides quick, inexpensive access to large amounts of information
- Requires minimal effort compared to primary data collection
- May reveal that the desired information already exists, eliminating the need for new data collection
- Can offer historical perspectives or large-scale datasets not feasible for individual researchers
Limitations:
- Quality and accuracy can vary substantially between sources
- Information may appear valuable initially but prove outdated, incomplete, or irrelevant upon closer examination
- Content may not precisely match the researcher's specific needs or objectives
- Lacks the researcher's direct control over data collection methods and standards
Common secondary data sources:
- Government databases (Census data, crime statistics)
- Academic journals and research publications
- Hospital records and medical databases
- Company records and organisational data
- Online databases and archives
Meta-analysis and effect size
Meta-analysis represents a sophisticated research technique that combines findings from multiple studies investigating the same topic. Often described as 'research about research', this approach provides a comprehensive overview by systematically reviewing and analysing results across numerous investigations.
Meta-analysis can involve qualitative reviews of conclusions from different studies or quantitative analysis that produces an effect size - a statistical measure indicating the overall strength of relationships between variables across all included studies.
Understanding Effect Size: Effect size provides a standardised measure that allows researchers to compare findings across different studies, even when they used different measurement scales or sample sizes. This is crucial for drawing meaningful conclusions from multiple research projects.
Key Points to Remember:
-
Qualitative data uses words and descriptions to capture rich, detailed experiences, while quantitative data employs numbers that can be statistically analysed
-
Primary data comes directly from your own research participants, whereas secondary data has been collected by others for different purposes
-
Each data type has distinct advantages: qualitative provides depth and context, quantitative enables objective measurement and comparison
-
Meta-analysis combines multiple research studies to produce overall conclusions and effect sizes that show the strength of relationships across investigations
-
The choice between data types depends on your research aims - neither qualitative nor quantitative approaches are inherently superior