DATA4207 · Data Analysis in the Social Sciences
Writing About Social Science Data I: Plan, Literature and Methods
Week 6 teaches the front half of a quantitative study: a sharp research question and aim, a hypothesis stated as both a general and a specific (directional, strength) claim, a literature review organised by variable, and a defensible data-and-methodology section. Grounded in the Research Project Outline checklist, this chapter maps directly onto how the Research Plan (20%) and the final report (50%) are marked, so the payoff is immediate.
What this chapter covers
- 01Introduction: context, a clearly stated research question/objective, and a roadmap of the paper
- 02Hypothesis stated two ways: a general claim and a specific directional + strength claim, falsifiable and grounded in the data
- 03Literature review — six steps: identify concepts, search, evaluate, synthesise, find gaps, position your study (synthesise, do not list)
- 04Methods section — five elements: design, participants/sample, data collection, data analysis, ethics
- 05Identifying dependent, independent and confounding variables and any transformations
- 06Justifying the model choice (no correct default, but wrong answers exist)
- 07Citation and formatting discipline; academic-integrity expectations (generative AI not permitted on assessed work)
- 08Research Plan structure and the ≥10-source literature requirement
Drafting the front half of a Research Plan
- +1Research question and aim: state it sharply and answerably, naming the dependent variable (turnout) and the key independent variable (median income), and give a one-line aim plus a roadmap of the plan.
- +2Hypothesis, stated twice: a general claim ('turnout rises with neighbourhood income') and a specific, directional, strength claim ('a one-SD increase in median income is associated with roughly X percentage points higher turnout'), so it is falsifiable and testable.
- +2Literature review: organise by variable, synthesise rather than list (agree/disagree, gaps, limitations), draw on at least ten sources beyond the set readings, and close by positioning your study in the identified gap.
- +1Data and methodology: name the data source and its biases, list the dependent, independent and confounding variables (with any transformations), and justify the chosen model — remembering there is no correct default, but there are wrong answers.
Key terms
- Research question
- A sharp, answerable question that names the outcome and the key predictor and drives the whole study. A strong introduction pairs it with an aim and a roadmap of the paper.
- Hypothesis (direction + strength)
- A falsifiable prediction stated both generally and specifically — including which way the relationship runs (direction) and how large it is expected to be (strength) — grounded in the data and prior literature.
- Literature review
- A synthesised, not listed, survey of prior work organised by concept or variable: evaluate sources, draw out agreements, debates and gaps, and position your study. The Research Plan requires at least ten sources beyond the set readings.
- Methodology section
- The five-part account of how the study is done: study design; participants/sample; data collection; data analysis (tests, software, reliability/validity); and ethical considerations. It must justify every analytic choice.
- Dependent / independent / confounding variables
- The outcome you explain (dependent), the predictors you test (independent), and the factors that bias the relationship if uncontrolled (confounding). The plan must identify all three and any variable transformations.
- Model justification
- The argument for why your chosen model (linear, logistic, or other) suits the outcome type and question. There is no correct default model, but there are wrong choices, so the justification is where marks are won or lost.
Writing About Social Science Data I: Plan, Literature and Methods FAQ
What does a strong hypothesis look like here?
It is stated at two levels and is falsifiable. The general form gives the expected relationship ('support rises with education'); the specific form adds direction and strength ('a one-category increase in education is associated with roughly X more predicted probability of support'). It should be grounded in your dataset and the literature, not plucked from intuition, so that the data could actually disprove it.
How do I write a literature review that isn't just a list?
Organise by concept or variable rather than by paper, and synthesise: for each theme say what the sources agree on, where they disagree, what the gaps and limitations are, and whether you agree and why. Then position your study in the gap you have identified. A run of 'Author (year) found... Author (year) found...' paragraphs is the classic low-scoring pattern.
How much of the Research Plan is the literature and methods?
The plan asks you to demonstrate that you have thought about the question, the data and the approach: a hypothesis and working theory, a literature review of at least ten sources beyond the set readings, and a methodology, with exploratory analysis but no full modelling required yet. The exact word budget and structure are on the Research Project Outline — confirm them on Canvas.
Can AI help me plan my report in DATA4207?
Yes, as a study aid — for understanding structure and checking reasoning, not for writing. Sia can explain what a strong research question, hypothesis, literature review and methods section look like and give feedback on the logic of your own draft. It does not write your assessment, and this unit does not permit generative AI on assessed work unless the coordinator explicitly allows it — always confirm on Canvas.
Assessment move
Write the front half early and iterate. Draft your research question in one sentence, then force yourself to state the hypothesis twice — general, then directional-and-strength — and check it is falsifiable against your data. Build the literature review by variable, keeping a running synthesis note (agree/disagree/gap) for each source rather than summarising papers one by one, and aim past the ten-source minimum. Sketch the methods as the five elements and write a paragraph justifying your model choice. Because the Week 6 skills are marked directly in the 20% plan and the 50% report, treat this as rehearsal for both, and confirm the outline, word counts and due dates on Canvas. Remember generative AI is not permitted on assessed writing here.
Working through Writing About Social Science Data I: Plan, Literature and Methods in DATA4207? Sia is AskSia’s AI Statistics tutor — ask any DATA4207 Writing About Social Science Data I: Plan, Literature and Methods 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.
