Data Recording, Analysis and Presentation

Data Recording, Analysis and Presentation

Data Recording Techniques

  • Qualitative data, which is not numerical, is usually recorded using field notes, audio or visual recording, or transcriptions of interviews. Transcribing ensures that all details are recorded accurately.
  • Quantitative data, which is numerical, is recorded using charts or spreadsheets. It’s important to keep careful, exact records of measurements and counts to ensure accuracy.

Data Analysis Techniques

  • Qualitative analysis requires a detailed review of the data to draw out themes, patterns and relationships. Thematic analysis and content analysis are common methods of analysing qualitative data.
  • Quantitative analysis involves statistical analysis. This can range from simple counts or percentages, to more advanced statistical tests, depending on the data and the research question.

Methods of Presenting Data

  • Graphs and charts are commonly used to visually represent quantitative data. Line graphs, bar charts and pie charts show data clearly and simply.
  • Tables can be used to neatly organise both qualitative and quantitative data.
  • Textual descriptions or summaries are often used in qualitative research, or to add context to quantitative displays of data.

Validity and Reliability

  • When analysing results it is crucial to ensure they are valid (the research measures what it is intended to) and reliable (the research could be replicated and yield the same results).
  • Measures to improve validity could include clear operationalisation of variables, control of extraneous variables, and use of standardised procedures.
  • Measures to improve reliability include repeated measures, inter-rater reliability, or use of a control group.

Data Interpretation

  • Interpretation involves making sense of the data gathered in the context of the research question and existing psychological theories or frameworks.
  • Inferential statistics may be used to test hypotheses or draw conclusions beyond the immediate data set. This usually involves statistical tests like the t-test or chi-squared test.
  • It’s important to evaluate the implications of the results and any potential limitations or biases in the research process.