Week 5: Planning Your Investigation
Group formation and research planning
One group member should accept the group assignment and create your team. The other members then click the same link and join the existing team — don’t create a new one. Clone the repo via GitHub Desktop.
Today’s goals
- Finalize your group and choose your project topic
- Set up your group’s GitHub repo with branches and pull requests
- Write a structured one-page research plan
- Present your plan to the class (60 seconds)
1. Choose your topic
Browse the curated topic list. Each topic has a clear research question, accessible data sources, and a genuine policy dimension.
Before committing, check with your instructor that no other group has chosen the same topic. Ask yourself:
- Can we access the data? (Download it now and check.)
- Does the question interest us enough for 6 weeks?
- Does it map to a statistical test we’ll learn (t-test, ANOVA, regression)?
2. Set up your group repo
Your instructor will demonstrate the Git collaboration workflow. Then your group does it for real:
Step-by-step
- Clone your group’s repo (created via Classroom 50 or by your instructor)
- Each member: create a branch with your name (e.g.
alex-explore) - On your branch: add your name to the
team.mdfile, save, commit - Push your branch to GitHub
- On GitHub.com: open a Pull Request from your branch to
main - A teammate: review, approve and merge your PR —
mainonly accepts changes through an approved PR, so you cannot merge your own - Everyone: pull the updated
main
This is the workflow you’ll use for the rest of the module. Branches keep your work separate until you’re ready to combine; PRs let teammates review before merging.
See the Git troubleshooting guide for the most common problems and fixes.
Ask on the class board, in Code Q&A. Someone else is likely stuck on the same thing, so asking in public helps them too. Demonstrators check it most weekdays, but they give classmates a chance to answer first.
The board is private to this class, so sign in to GitHub first. If the link shows “404 – page not found”, you’re not signed in, or you haven’t accepted the Classroom 50 invitation yet.
3. Write your research plan
Use the template below (also available as a markdown file in your repo). Complete all seven sections as a group.
Your instructor and demonstrators will circulate to challenge your design: “What’s your control?” “How will you handle this confounder?” “Is your sample representative?”
Research plan template
# Research Plan: [Your topic title]
## Problem
### 1. Research question
What are you investigating? (One sentence.)
## Plan
### 2. Hypothesis
What do you expect to find, and why?
### 3. Data sources
Where will your data come from? What variables? What time period?
### 4. Comparison / control
What are you comparing to? How will you isolate the effect of
interest?
### 5. Potential confounders
What alternative explanations should you worry about?
### 6. Analysis plan
What statistical tools do you anticipate using? (Descriptive stats,
t-tests, ANOVA, regression — link to what you've learned and what's
coming in Weeks 6–8.)
## 7. Division of labour
Who's doing what this week and next?→ Download the research plan template
4. Present your plan
Each group gives a 60-second pitch:
- Our question is…
- We hypothesize that…
- Our data comes from…
- Our comparison is…
The class and instructor give brief feedback. Focus on:
- Is the question answerable with the available data?
- Is there a clear comparison?
- What’s the biggest potential confounder?
Extension: break Git on purpose
Optional — for groups who get through the workflow quickly. Nothing later in the module depends on this, but the hour you spend here is an hour you will not lose to a merge conflict in Week 9.
- Manufacture a conflict. Two of you edit the same line of
team.mdon different branches, commit, and both open PRs. Merge one. What does GitHub say about the other? Resolve it — in GitHub Desktop, or on the web — and write down inteam.mdwhat the conflict markers meant. - Find out what a PR review can do. Leave a line comment on a teammate’s PR rather than approving it silently. Request a change and have them push a fix to the same branch; watch the PR update itself without a new PR being opened.
- Test the guard on
main. Your repo only accepts changes tomainthrough a pull request that a teammate has approved. Commit something directly onmainand try to push it: read the error. Then rescue the commit — move it onto a branch and open a PR. What does the rule cost your group, and what does it buy? - Write a
.gitignoreentry that matters. Put a large data file in your repo, commit it, then work out why removing it in a later commit does not make the repo smaller. This is the single most common irreversible mistake students make with Git.
Commit and wrap-up
Commit your research plan via a pull request:
- One group member writes the plan in
research-plan.md - Commit and push to a branch
- Open a PR — other members review
- Merge to
main
Preview: Next week you’ll learn the formal tools for testing hypotheses — t-tests, p-values, and why they can mislead you. You’ll start applying them to your project data.