Week 14 · Suggested 2–4 hours · First-pass draft
A research report that can survive scrutiny
Complete the final reproducible statistical investigation and demonstrate that you can communicate uncertainty, data provenance, and limitations.
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
- Select an appropriate real dataset, or the documented airquality dataset, and write an empirical question the design can answer.
- Audit the source, units, missingness and transformations, and produce at least two appropriate figures.
- Run a justified inferential or modeling method, report estimates and uncertainties, and conduct one sensitivity analysis.
- Deliver a transparent script and a written report, with a self-critique of unsupported conclusions.
What to submit
Complete 100-point capstone report with accompanying reproducible code and a data provenance note.
Self-check before finishing
A second reader should be able to rerun the analysis and explain precisely which claims are and are not justified.
Assigned reading
Fit a multivariable model, document the analysis, and submit a transparent report.
- Lesson 43: multivariable airquality
- Lesson 44: reproducible research and reporting
- Lesson 45: capstone research project
Instructor discussion guidance
Use the published capstone rubric; independent human review is essential and the site grants no academic credit.
Print a predict–experiment–explain worksheet → · Open browser R →