Your question, your plan

Research Methods — Week 5 Application

Today’s plan

Goals

By the end of today:

1. Your group is finalised
2. Your topic is chosen
3. Your group GitHub repo is set up
4. Your one-page research plan is committed

• [10 min] Finalise groups. Any students without a group join one now. Distribute the full topic list with data source descriptions.

Questions?

Submit questions anonymously:

PollEv.com/geol

text geol to 07480 781235

• Open the Poll Everywhere Q&A activity before the session and leave it active throughout.
• Questions appear in your Poll Everywhere presenter view; upvoted questions rise to the top.
• Address during transitions or at the end of concept blocks, not mid-explanation.
• Reset (archive) the activity between sessions so questions don’t carry over from the previous week.

Git collaboration

🎓💻 Working as a team

The group workflow

Phase 1 (individual)

1. Clone
2. Edit
3. Commit
4. Push

Phase 2 (group)

1. Clone the shared repo
2. Create a branch
3. Edit, commit, push the branch
4. Open a Pull Request
5. Teammate reviews and merges

• [15 min] Demonstrate the full workflow live with GitHub Desktop. Go slowly — this is new.

Live demo

🖥️ Switching to GitHub Desktop

1. Clone the group repo
2. Create a branch: add-my-name
3. Edit team.md — add your name
4. Commit → Push the branch
5. Open a Pull Request on GitHub.com
6. Teammate reviews → Merge

• Narrate each step. Show the PR interface on GitHub.
• Emphasise: branches keep work separate until ready. PRs let teammates review before merging.

Why branches?

Without branches: everyone edits the same files → conflicts.

With branches: you work in parallel → combine when ready.

Think of it like lab notebooks: everyone writes their own notes, then you compile the report together.

Set up your repos

✏️📋 Dry run

Do it yourself

Each group member:

1. Clone the group repo
2. Create a branch with your name
3. Add your name to team.md
4. Commit, push, open a PR
5. The group merges all PRs

Raise your hand when your group has merged everyone’s PR.

• [15 min] This will be messy. Expect confusion about branches, merge conflicts on team.md, and at least one group pushing to main. That’s the learning.
• Demonstrators prioritise groups who are stuck.

Research plan

✏️💬 Drafting your plan

The template

Your repo contains research-plan.md with seven sections:

1. Research question (one sentence)
2. Hypothesis (what you expect and why)
3. Data sources (where, what variables, what period)
4. Comparison / control (what are you comparing to?)
5. Potential confounders
6. Analysis plan (which tools: descriptive, t-test, ANOVA, regression?)
7. Division of labour

• [40 min] Groups draft their plans. Circulate and challenge: “What’s your control?” “How will you handle this confounder?” “Is your sample representative?”

Questions to challenge you

As you draft, we’ll be asking:

• What’s your control?
• How will you isolate the effect?
• Is your sample representative?
• What assumptions are you making?

• These should feel familiar by now — they’re the same questions from Weeks 1–4, applied to new topics.

Plan presentations

💬 60-second pitches

Share your plan

Each group: 60 seconds.

1. What’s your question?
2. What’s your hypothesis?
3. Where does your data come from?
4. What’s your comparison?

• [15 min] Brief feedback from class and instructor. Focus on: is the question answerable? Is there a clear comparison?

Wrap-up

Before you leave

• Group repo is set up and everyone can push
• Research plan is committed (via PR)
• Topic is finalised

Next week: “Testing hypotheses”

You’ll learn formal tools for testing your hypotheses — and why a significant p-value doesn’t always mean what you think.

• Groups who can’t decide on a topic should be gently pushed — indecision costs more than a suboptimal choice.