DATA4207 · Data Analysis in the Social Sciences
Writing About Social Science Data II: Results, Discussion and Conclusion
Week 10 teaches the back half of the report — presenting and carefully interpreting results, writing an honest discussion of limitations and future work, and a conclusion that answers the hypothesis and research question. You also apply the Week 9 mapping techniques to finish the spatial group project. The second assessable group project (8%) is due, and these skills carry straight into the 50% individual report.
What this chapter covers
- 01Results section — present data objectively, systematically, statistically and visually
- 02Statistical write-up template: coefficient sign/size, statistical significance, model fit, baseline comparisons
- 03Captioning and referencing figures; highlighting trends in the text
- 04Discussion: interpret results, relate to literature and theory, evaluate strengths and limitations
- 05Being cautious about causation unless the design supports it (cross-sectional designs limit causal claims)
- 06Conclusion: answer the hypothesis, summarise methods and findings, implications and future directions
- 07General writing rules: no new results in the discussion, no over-generalising, always tie back to the literature
- 08Applying mapping techniques to finish Group Project 2 (8%, due Week 10)
Turning a coefficient into results, discussion and a limitation
- +2Results (objective + statistical): 'The coefficient for X is 0.45, indicating a positive association with Y, and it is statistically significant (p < 0.05), suggesting a meaningful relationship.' Keep it factual — no interpretation yet in a stand-alone results section.
- +1Model fit: report adjusted R² ≈ 0.19, i.e. the model explains about 19% of the variance in Y. State it honestly rather than dressing up a modest fit.
- +2Discussion: interpret and connect to the literature — 'this aligns with Smith et al. (2020) but extends their work by...' — then weigh what the finding means and its significance, without introducing any new results.
- +1Limitations and conclusion: because the design is cross-sectional, describe the relationship as an association, not a cause, and note this as a limitation with a future-work direction. Conclude by answering the hypothesis and research question directly.
Key terms
- Results section
- The factual presentation of what the data show — objective, systematic, statistical and visual — reporting coefficients, significance, fit and baseline comparisons without drawing conclusions.
- Discussion section
- Where you interpret the results, relate them to the research question, literature and theory, evaluate strengths and limitations, and suggest future directions — being cautious about causation unless the design supports it.
- Conclusion section
- The closing that restates and answers the hypothesis, summarises methods and key findings, discusses implications and suggests concrete future research — specific, not vague or repetitive.
- Adjusted R-squared
- The proportion of outcome variance explained, penalised for the number of predictors. Reporting it honestly (e.g. ~0.19 = ~19% explained) is expected rather than hiding a modest fit.
- Causation caveat
- The rule that a relationship should be described as an association, not a cause, unless the study design (e.g. an experiment) supports a causal claim. Cross-sectional designs in particular limit causal inference.
- Combined results and discussion
- A permitted structure that merges the results and discussion sections to save words while still keeping factual reporting and interpretation clearly signposted.
Writing About Social Science Data II: Results, Discussion and Conclusion FAQ
How should I write up a coefficient in the results?
Follow the template: state the coefficient's sign and size, whether it is statistically significant, and how it compares to the baseline, keeping the language factual. For example, 'the coefficient for X is 0.45, a positive and statistically significant (p < 0.05) association with Y.' Save the interpretation of what it means for the discussion; a stand-alone results section reports, it does not conclude.
When can I claim causation?
Only when the design supports it. Most social-science reports in this unit use observational or cross-sectional data, which can establish association but not cause, so you describe relationships as associations and flag the limitation explicitly. Over-claiming causation from a cross-sectional model is a common way to lose marks in the discussion.
What makes a weak conclusion?
Vagueness and repetition — 'social media is bad, more research is needed' — with no specific findings or implications. A strong conclusion answers the hypothesis directly, summarises the key findings and their significance, acknowledges limitations, and points to concrete future directions, without introducing any new results.
Can AI help me write up results in DATA4207?
Yes, as a study aid — for structure and feedback, not for writing your report. Sia can explain the results/discussion/conclusion craft and check whether your draft is objective, linked to the literature, and appropriately cautious about causation. It does not write your graded assessment, and this unit does not permit generative AI on assessed work unless the coordinator explicitly allows it — confirm on Canvas.
Assessment move
Practise the whole back half on a single model you have already fitted. Write the results objectively and statistically (coefficient, significance, fit, baseline), then a discussion that interprets and links to the literature with the 'aligns with... but extends...' move, then a conclusion that answers the hypothesis. Drill two habits that protect marks: never introduce new results in the discussion, and always hedge causation for observational or cross-sectional data. Report a modest adjusted R² honestly rather than hiding it. Because Group Project 2 (8%) is due this week and these skills feed the 50% individual report, treat every write-up as rehearsal for the report, and confirm the project requirements and due date on Canvas. Remember generative AI is not permitted on assessed writing here.
Working through Writing About Social Science Data II: Results, Discussion and Conclusion in DATA4207? Sia is AskSia’s AI Statistics tutor — ask any DATA4207 Writing About Social Science Data II: Results, Discussion and Conclusion question and get a clear, step-by-step explanation grounded in how DATA4207 is taught and assessed. Read this chapter free, then take your hardest questions to Sia.
