Theme: Making Sense of Quantitative and Qualitative Data through Systematic Analysis
Duration: 1 week (self-paced)
Level: MA / MSc / PhD Preparation
Format: Fully self-contained lesson for independent study
đ· 11.1 Purpose of This Module
Data analysis and interpretation transform raw information into coherent, evidence-based insights. This module helps you conduct analysis that is methodologically aligned, logically structured, and clearly reportedâwhether you’re working with numbers, text, or both.
By the end, you will be able to:
- Understand the goals and principles of data analysis
- Select appropriate analysis techniques based on your method
- Conduct structured qualitative coding or statistical tests
- Interpret findings in context, not just report them
- Avoid common mistakes and ensure analytical rigour
đ 11.2 What Is Data Analysis?
Data analysis is the process of organising, examining, and transforming data to uncover patterns, relationships, and meaning that address your research question.
Analysis is always followed by interpretationâanswering the “So what?” and “What does this mean?” questions in light of your aims.
đ§Ș 11.3 Quantitative Data Analysis
â A. Descriptive Statistics
Summarise and visualise the basic features of your data.
| Measure | Function | Example |
|---|---|---|
| Mean | Average value | Mean weekly study time = 12 hours |
| Median | Midpoint value | Median income = ÂŁ21,000 |
| Standard Deviation (SD) | Spread of scores | SD = 2.3 for test scores |
| Frequencies | Counts or percentages | 65% female, 35% male respondents |
Visuals: Bar charts, histograms, pie charts, box plots
â B. Inferential Statistics
Used to test hypotheses and generalise to populations.
| Test | Purpose | Example |
|---|---|---|
| T-test | Compare two means | Do men and women differ in stress levels? |
| ANOVA | Compare >2 groups | Are there GPA differences across 3 teaching styles? |
| Correlation (Pearsonâs r) | Assess relationships | Time spent revising vs exam score (r = .65) |
| Chi-square | Categorical association | Gender vs programme preference |
| Regression | Predict outcomes | Predicting satisfaction from workload and support |
â Always check:
- Assumptions (normality, independence)
- P-values (commonly < 0.05 indicates significance)
- Effect sizes (strength of findings, not just significance)
đ 11.4 Qualitative Data Analysis
â A. Thematic Analysis (Widely Used)
Systematically identifying patterns or âthemesâ in textual data.
Steps:
- Familiarisation â Read data multiple times
- Initial Coding â Label meaningful segments
- Theme Generation â Group related codes
- Review Themes â Refine or merge themes
- Define and Name Themes â Create meaningful labels
- Interpret and Present â Relate back to research question
| Code | Quote | Emerging Theme |
|---|---|---|
| âItâs hard to speak in classâ | âIâm scared to say something wrongâ | Fear of judgement |
| âI use AI to get ideasâ | âIt helps me brainstormâ | AI as inspiration tool |
| âMy tutor doesnât like itâ | âShe called it cheatingâ | Conflicting views on AI |
â B. Other Qualitative Approaches
| Approach | Focus | Example |
|---|---|---|
| Content Analysis | Count presence of themes/words | Count how often âfreedomâ appears in campaign leaflets |
| Narrative Analysis | Examine personal storiesâ structure and meaning | Study turning points in refugee resettlement stories |
| Discourse Analysis | Study language and power | How government talks about âbenefits cheatsâ |
â Tools: NVivo, Atlas.ti, manual coding in Word/Excel
đ 11.5 Mixed Methods Data Integration
When using both qualitative and quantitative data:
| Integration Point | Example |
|---|---|
| At Analysis | Quant survey shows low motivation; Qual interviews explain causes |
| At Interpretation | âWhile 70% feel demotivated, they describe it as frustration with unclear tasks.â |
| At Reporting | Merge both into discussion with linked themes and charts |
â 11.6 Common Mistakes to Avoid
| Mistake | Why Itâs a Problem | What to Do Instead |
|---|---|---|
| Reporting data with no interpretation | Lacks meaning | Always ask: âWhat does this show?â |
| Ignoring negative or unexpected results | Biased or incomplete | Explore and explain them |
| Overgeneralising from small samples | Weakens credibility | Be transparent about limitations |
| Misaligning analysis with question | Disjointed argument | Keep your research aim in view throughout |
đ 11.7 Self-Learning Task Set (Independent Exercises)
âïž TASK 1: Plan Your Analysis
Write a short plan (~200 words) covering:
- Your research question and design
- The type of data you are collecting
- What analysis technique you will use
- How you will interpret results based on your aims
Example Output:
My project explores how AI-assisted writing tools affect studentsâ learning experiences. I will collect interview data from 10 students and analyse it using thematic analysis. I will code transcripts manually, look for recurring patterns, and group them under broader themes. I aim to relate findings to theories of self-directed learning and academic agency.
đ TASK 2: Do a Basic Quant Analysis Simulation
Invent a small dataset:
| Hours Studied | Exam Score |
|---|---|
| 2 | 60 |
| 4 | 70 |
| 6 | 80 |
| 8 | 85 |
| 10 | 90 |
Now:
- Calculate mean hours studied and mean score
- Plot a simple line graph
- Comment on the relationship you see
Expected: Positive correlationâmore study â higher scores
đ§ TASK 3: Simulate Coding Qualitative Data
Use this sample quote:
âI feel anxious when I write essays. But when I use AI tools, itâs like having someone to bounce ideas off. It helps me get started.â
- Highlight 2â3 phrases of interest
- Assign codes to each
- Suggest a possible theme
Example:
- âfeel anxiousâ â Code: academic anxiety
- âbounce ideas offâ â Code: AI as peer support
- Theme: Emotional relief through digital assistance
đ TASK 4: Interpret a Combined Dataset (Mixed Methods)
Scenario:
- 70% of students report increased motivation using AI tools
- Interviews reveal students say: âIâm more motivated when I feel in control of the writing process.â
Write 3â4 sentences combining these into a meaningful interpretation.
Example Output:
Quantitative findings show that a majority of students feel more motivated when using AI tools. This is supported by qualitative responses, which suggest that motivation increases when students experience a sense of autonomy. Together, the data indicate that AIâs role in scaffolding tasks enhances emotional engagement.
đ 11.8 Summary of Key Takeaways
- Data analysis transforms information into insight
- Choose analysis methods that fit your design (qual = themes; quant = stats)
- Analysis is not just technicalâit requires interpretation and reflection
- Mixed methods must synthesise, not just parallel present
- Clear, logical, and honest reporting builds trust and academic value
â End-of-Module Self-Evaluation Checklist
| Concept | Yes / No |
|---|---|
| I identified an appropriate analysis method for my data | â |
| I understand the steps in either statistical or thematic analysis | â |
| I created a mini dataset and analysed it (quant or qual) | â |
| I interpreted a result using academic reasoning | â |
| I can explain how my analysis addresses my research question | â |