analyze-stats

Files (83)

• SKILL.md
• agreement_reliability.md · references/analysis_guides/
• burden_decomposition_forecasting.md · references/analysis_guides/
• calibration.md · references/analysis_guides/
• diagnostic_accuracy.md · references/analysis_guides/
• health_economic_evaluation.md · references/analysis_guides/
• mediation.md · references/analysis_guides/
• mendelian_randomization.md · references/analysis_guides/
• meta_analysis.md · references/analysis_guides/
• missing_data.md · references/analysis_guides/
• multiplicity.md · references/analysis_guides/
• network_meta_analysis.md · references/analysis_guides/
• nhis_icd10_mapping.md · references/analysis_guides/
• polygenic_risk_score.md · references/analysis_guides/
• propensity_score.md · references/analysis_guides/
• regression.md · references/analysis_guides/
• repeated_measures.md · references/analysis_guides/
• survey_weighted.md · references/analysis_guides/
• survival.md · references/analysis_guides/
• test_selection.md · references/analysis_guides/
• analysis_run_workflow.md · references/
• figure_style.mplstyle · references/style/
• theme_publication.R · references/style/
• ajr.yaml · references/table-standards/journal-profiles/
• european_radiology.yaml · references/table-standards/journal-profiles/
• jama.yaml · references/table-standards/journal-profiles/
• lancet.yaml · references/table-standards/journal-profiles/
• nejm.yaml · references/table-standards/journal-profiles/
• radiology.yaml · references/table-standards/journal-profiles/
• table-standards.md · references/table-standards/
• agreement.md · references/table-standards/table-types/
• diagnostic_accuracy.md · references/table-standards/table-types/
• incremental_value.md · references/table-standards/table-types/
• meta_analysis.md · references/table-standards/table-types/
• model_comparison.md · references/table-standards/table-types/
• reader_study.md · references/table-standards/table-types/
• regression_results.md · references/table-standards/table-types/
• survival_results.md · references/table-standards/table-types/
• table1_demographics.md · references/table-standards/table-types/
• tool-comparison.md · references/table-standards/
• agreement_analysis.py · references/templates/
• dca_plot.R · references/templates/
• diagnostic_accuracy.py · references/templates/
• dta_meta_analysis.R · references/templates/
• forest_plot.py · references/templates/
• likert_summary.py · references/templates/
• meta_analysis.R · references/templates/
• propensity_score.py · references/templates/
• regression.py · references/templates/
• repeated_measures.py · references/templates/
• sample_size.R · references/templates/
• survey_weighted_analysis.py · references/templates/
• survival_analysis.py · references/templates/
• table1_demographics.py · references/templates/
• README.md · scripts/analysis_run_challenge/
• verify.sh · scripts/analysis_run_challenge/
• check_generated_code.py · scripts/
• check_separation.py · scripts/
• demo_analysis_run.py · scripts/
• rating_monotonicity.py · scripts/
• …and 23 more

SKILL.md (first lines)

# Statistical Analysis Skill

Generate reproducible code (Python preferred, R when necessary) for medical research analyses,
run it, and produce publication-ready tables and figures from its output.

## Data Privacy Check

Before reading any data file, check whether it might contain Protected Health Information (PHI):

1. If `*_deidentified.*` files exist in the working directory, use those.
2. If only raw CSV/Excel files exist, ask the user whether the data contain patient identifiers
   (names, national ID / RRN, contact details); if so, have them de-identify it first with
   `/deidentify`.
3. Proceed once the user confirms the data are de-identified or contain no PHI.
4. **NEVER** display raw PHI values (names, phone numbers, RRN) in your output, because console
   output is copied into transcripts and drafts. If you encounter them, warn the user and suggest
   `/deidentify`.

## Reference Files

- `${CLAUDE_SKILL_DIR}/references/templates/` — reusable analysis scripts; read the matching one
  before generating code.
- `${CLAUDE_SKILL_DIR}/references/analysis_guides/` — methodology guides; the Phase 2 table says
  which to read.
- `${CLAUDE_SKILL_DIR}/references/table-standards/` — `table-standards.md` (universal and AMA
  rules, footnote order, gtsummary pipeline), `journal-profiles/` (YAML per journal: radiology,
  jama, nejm, lancet, european_radiology, ajr), `table-types/` (one template per table type),
  `tool-comparison.md` (R/Python table tools).
- `${CLAUDE_SKILL_DIR}/references/style/figure_style.mplstyle` — figure style.

## Workflow

### Phase 1: Data Assessment

1. **Read the data file** (CSV, Excel, TSV, or other tabular format).
2. **Report to the user**: shape (rows x columns); column names and inferred types (continuous,
   categorical, ordinal, binary, datetime); missing values per column (count and percentage);
   first 5 rows; unique value counts for categorical columns.
3. **Identify the analysis unit**: patient, exam, lesion, image, rater, study, etc.
4. If a variable name or coding is uncertain, write `[VERIFY: variable_name]` and ask the user to
   confirm it against the data dictionary; never guess a column name or coding.

### Phase 2: Analysis Plan

**Observational designs** (cohort, case-control, cross-sectional, registry, survey): before
planning, look for a `variable_operationalization.md` from `/define-variables` (or an equivalent
codebook-backed definition table). If none exists, warn the user and recommend running
`/define-variables` first, because exposure/outcome/covariate definitions and cutoffs invented
ad hoc from the data dictionary are a common reason reviewers reject observational work. This is
a warning, not a block: proceed on explicit user confirmation and record that the artifact was
not available.

Propose an analysis plan; the user decides the research question and endpoints. Mark any
clinical definition, cutoff, diagnostic criterion or guideline claim you could not confirm
`[VERIFY]`.

1. **Detect the analysis type** from the table in Analysis-Specific Guidelines, or accept the
   user's specification.
2. **List the specific tests** to be performed.
3. **Identify primary and secondary endpoints**.
4. **State the assumptions** that will be checked (normality, homogeneity, independence).
5. **Note data cleaning** needed (recoding, outlier handling, missing-data strategy).
6. **Anchor the estimand to the research question.**
   - Interaction, synergy or effect modification: the primary estimand is the **interaction
     parameter itself** (a likelihood-ratio test of the interaction term, or the interaction
     OR/HR on one stated scale) — not a main-effect OR whose CI is then read as "no synergy". A
     public-health or biological **synergy** claim is additive-scale: report **RERI**, **AP** or
     **S**, each with a CI (R `interactionR` / `epiR`; Knol & VanderWeele reporting), not only a
     multiplicative product term, because a non-significant multiplicative interaction is
     compatible with a large additive one (and vice versa). Joint categories (high/high vs
     low/low) show joint association, not interaction; "stronger in A than in B" from separate
     stratum estimates is the difference-in-significance fallacy — report the formal interaction
     term.
   - Equivalence or non-inferiority: declare the margin up front (a TOST procedure, or the CI
     compared against a pre-stated MCID); a non-significant difference is not equivalence
     without a margin.
7. **Screen every categorical/binary predictor for separation before fitting anything.** A
   predictor that perfectly predicts the outcome has no finite MLE, and the failure is silent:
   `glm` returns an odds ratio near 0 (or enormous), *p* ≈ 0.99, and an AUC that ends up in a
   table. Pathognomonic imaging signs (T2-FLAIR mismatch, the string sign, a halo sign) cause
   it routinely: 100% specificity means an empty cell by construction.

   ```bash
   python3 "${CLAUDE_SKILL_DIR}/scripts/check_separation.py" \
     --data cohort.csv --outcome idh_mutant --auto --strict
   ```

   `COMPLETE_SEPARATION` (an empty cell) and `QUASI_SEPARATION` (a cell below the sparsity
   floor) both halt the plan. With two or more predictors the script also tests them jointly
   (a linear combination can separate the outcome when no single predictor does); that test
   needs scipy, and without it the report says the joint check was not run. The remedy is a **design** decision, made in the plan: Firth's
   penalised likelihood keeps one model, while a **two-stage rule** — classify the sign-positive
   cases directly, model only the sign-negative remainder — is usually the clinically meaningful
   choice for a pathognomonic sign, because a sign-positive patient is already diagnosed.

Present the plan and **wait for user approval** before executing.

### Phase 3: Execute

Generate and run a Python (preferred) or R script. Every number you report **MUST** come from
its executed output, never estimated or hand-typed, because a number no script reproduces cannot
be verified.

#### Script Structure

Start every script with a reproducibility header:

```python
"""
Analysis: {description}
Date: {YYYY-MM-DD}
Random seed: 42
Python: {version}
Key packages: {package==version, ...}
"""
import numpy as np
import pandas as pd
np.random.seed(42)
```

From Aperivue/medsci-skills, MIT.

More from Aperivue/medsci-skills