Week 8 · Suggested 90 minutes · First-pass draft
What do two groups tell us?
Choose between independent, paired, and binary-outcome comparisons based on design.
Applied assignment, not a stored grade. Instructions and model checks are provided for self-study or instructor adaptation. Work is not transmitted to this site.
What you will do
- Use the fictional independent score groups from the Welch lesson; calculate the difference of means and standard error.
- Run the R Welch procedure and interpret its interval without claiming a causal group effect.
- Reanalyze the five fictional paired before/after students using their within-person differences.
- Compute the difference in proportions, risk ratio, and odds ratio for .60 versus .40 success rates.
What to submit
A decision tree identifying the correct procedure for each study and a worked statistical interpretation.
Self-check before finishing
Independent mean difference 2.5; its approximate standard error 1.803. Paired mean change 4.2.
Assigned reading
Analyze independent means, paired changes, and differences in proportions.
- Lesson 25: two sample means
- Lesson 26: paired comparisons
- Lesson 27: two proportions and risk differences
Instructor discussion guidance
Check that the student does not create artificial pairs and does not confuse risk ratio with odds ratio.
Print a predict–experiment–explain worksheet → · Open browser R →