Fix 10 API discrepancies in quickstart.rst

[igerber]

Summary

• Fix generate_did_data() parameter: treatment_start → treatment_period
• Fix DifferenceInDifferences.fit() parameters: treated → treatment, post → time
• Fix DifferenceInDifferences constructor: cluster_col → cluster
• Fix TwoWayFixedEffects.fit() parameter: treated → treatment
• Fix MultiPeriodDiD: move reference_period from constructor to fit()
• Fix MultiPeriodDiD.fit(): replace treatment_start with post_periods
• Fix CallawaySantAnna results attribute: att → overall_att
• Fix check_parallel_trends(): correct import path and parameters
• Fix HonestDiD: update to use method/M instead of delta=DeltaRM, and ci_lb/ci_ub instead of robust_ci
• Fix plot_event_study import path: diff_diff → diff_diff.visualization

Methodology references (required if estimator / math changes)

• N/A - documentation-only changes, no methodology code modified

Validation

• Tests added/updated: No test changes needed (documentation only)
• All 10 API fixes verified against actual implementation using Python introspection
• Imports and parameter names confirmed correct via automated checks

Security / privacy

• Confirm no secrets/PII in this PR: Yes

---

Generated with Claude Code

[github-actions]

Overall Assessment: ⚠️ Needs changes

Executive Summary

• Docs-only update; no estimator/math changes; Methodology Registry unaffected.
• Most API name fixes now align with in-code signatures (DiD, TWFE, MultiPeriodDiD, HonestDiD).
• Event study example still errors with the quickstart data because reference_period=-1 is not present in period.

Methodology

• No findings.

Code Quality

• No findings.

Performance

• No findings.

Maintainability

• No findings.

Tech Debt

• No findings.

Security

• No findings.

Documentation/Tests

• P2 | Impact: Event-study snippet raises ValueError when using the earlier quickstart data (periods 0–9) because reference_period=-1 is not in the time column. | Concrete fix: set reference_period to an existing pre-period (e.g., 4) or add create_event_time(...) and use time='event_time' with reference_period=-1. (docs/quickstart.rst:127)

[igerber]

/ai-review

[github-actions]

🔁 AI review rerun (requested by @igerber)

Head SHA: ff0c55784fa6ac5cd0b539d7ca0d2704b7f12266

---

Overall assessment: ✅ Looks good

Executive Summary

• Quickstart examples now align with current API names and return values; no estimator logic changed.
• Methodology registry alignment is unaffected because the diff is documentation-only.
• Doc examples were not executed (residual risk: runtime drift if APIs change later).

Methodology

• No findings.

Code Quality

• No findings.

Performance

• No findings.

Maintainability

• No findings.

Tech Debt

• No findings.

Security

• No findings.

Documentation/Tests

• No findings.