Add RD/RKink sensitivity-checks walkthrough

[drbenvincent]

Closes #790

Summary

Follow-up to #785: documents how to use the pipeline-style sensitivity checks for {term}`Regression discontinuity design` and {term}`Regression kink design` workflows, mirroring the staggered-DiD walkthrough that landed in `staggered_did_pymc.ipynb`.

• New Sensitivity analysis section in `rd_pymc.ipynb` with a Related-checks summary, numbered walkthrough, executed pipeline cell running `BandwidthSensitivity` + `McCraryDensityTest`, an HTML-report iframe, pass/fail interpretation, and an If these checks fail troubleshooting block.
• Refresh of the existing sensitivity section in `rkink_pymc.ipynb` with the same structure: links to `pipeline_workflow` and the central `sensitivity_checks` guide, a Related-checks block clarifying that `McCraryDensityTest`, `PlaceboInTime`, `LeaveOneOut`, and `PlaceboInSpace` are not applicable to RKink, a numbered walkthrough, pass/fail interpretation, and an If this check fails troubleshooting block.
• Docs only — no code changes.

Notes

• The bandwidth sweep in `rd_pymc.ipynb` uses the linear interaction formula `y ~ 1 + x + treated + x:treated` rather than basis splines, with an inline note explaining why: `bs(x, df=6)` bakes its knots into the full data and patsy raises an error if a narrower bandwidth subset asks the model to evaluate observations that fall outside those baked-in outer knots.
• The McCrary check fails on the bundled `rd` dataset purely because the running variable spans `[-1, 1]` while the threshold sits at `0.5`. The notebook flags this explicitly so readers don't read the failure as evidence of manipulation in the example data.

Test plan

• `prek run --all-files` passes (notebook schema, ruff format, codespell, mypy, BibTeX, etc.)
• Both notebooks validate with `nbformat.validate`
• `rd_pymc.ipynb` sensitivity pipeline cell executes successfully (real outputs committed)
• CI passes on this PR
• Visual review of the rendered docs page

Made with Cursor

[review-notebook-app]

Check out this pull request on 

See visual diffs & provide feedback on Jupyter Notebooks.

---

Powered by ReviewNB

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 94.59%. Comparing base (deb8774) to head (1444e3f).
⚠️ Report is 1 commits behind head on main.

Additional details and impacted files

@@            Coverage Diff             @@
##             main     #872      +/-   ##
==========================================
- Coverage   94.60%   94.59%   -0.02%     
==========================================
  Files          80       80              
  Lines       12764    12764              
  Branches      770      770              
==========================================
- Hits        12076    12074       -2     
- Misses        485      486       +1     
- Partials      203      204       +1     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

[read-the-docs-community]

Documentation build overview

📚 causalpy | 🛠️ Build #32485165 | 📁 Comparing 1444e3f against latest (deb8774)

  🔍 Preview build  

3 files changed

± 404.html
± notebooks/rd_pymc.html
± notebooks/rkink_pymc.html