Overview | Basic workflow | Step by step | Configuring an LLM provider | Relationship to confoundvis | References

Overview | 1. Load Package and Data | 2. Build the Governance Object | 3. Check Which Laws Apply | 4. EEOC Adverse Impact Analysis (4/5ths Rule) | 5. NYC Local Law 144 Bias Audit | 6. NIST AI RMF Checklist | 7. Risk Classification | 8. Generate an Audit Report | 9. Checklist Reference | References

Overview | Installation | Step 1: Simulate Data | Step 2: Estimate ATT(g,t) | Step 3: Pre-Treatment Falsification Test | Step 4: Aggregate into Event Study | Step 5: Cohort-Level Aggregation | Step 6: Spillover Estimates | Bandwidth Selection | References

Background | The Example Dataset | Fitting the Model | Full Report | The DASB Test | AI-Effect Classification | Visualisations | Simulation | References

Overview | Simulated dataset | Step 1: Validate panel data | Step 2: Build decision paths | Aggregate transition matrix | Step 3: Drift Intensity Index (DII) | Step 4: Group trajectories and Bias Amplification Index (BAI) | Step 5: Temporal Fragility Index (TFI) | Interpretation guide | Step 6: Exporting a reproducible R script | Step 7: Launch the interactive app | Citation | Session info

Overview | 1. Prepare event data | 2. Build a monthly graph series | 3. Structural metrics | 4. Community dynamics | 5. Network Drift Index (NDI) | 6. User role trajectories | 7. Visibility & inequality | 8. Group disparity audit | Summary

Overview | 1. Descriptive statistics | 2. t-Test | 3. One-way Analysis of Variance (ANOVA) | 4. Two-Way Analysis of Variance (ANOVA) with simple effects | 5. Analysis of Covariance (ANCOVA) with adjusted means | 6. Multivariate Analysis of Variance (MANOVA) | 7. Post-hoc pairwise comparisons | 8. Chi-square test | 9. Proportion test with risk difference, risk ratio, and odds ratio | 10. Regression table | 11. Robust regression (Heteroscedasticity-Consistent standard errors) | 12. Heteroscedasticity diagnostics | 13. Multilevel model reporting | 14. Exporting to Word | 15. APA figures

Overview | 1. Simulate Clustered Data | 2. Estimate Propensity Scores | 3. Check Overlap | 4. Build Inverse Probability Weights | 5. Check Balance | 6. Estimate the ATT | 7. Sensitivity Analysis | Alternative: Dual-Balance Matching | Summary

Overview | Simulated data | Fitting the model | 1. Love Plot — plot_balance() | 2. Dose-Response Curve — plot_mediation() | 3. Sensitivity Contour — plot_sensitivity() | 4. Diagnose — diagnose() | Clustered data | Theoretical note on the sensitivity contour

Overview | The Synthetic Lending Dataset | Step 1 — Build the Audit Object | Step 2 — Describe Bias Trajectories | Trajectory Plot | Heatmap — Disparity Surface | Step 3 — Transition Analysis | Markov State Evolution | Step 4 — Amplification Analysis | Narrative Interpretation | Step 5 — Covariate Adjustment | Step 6 — Bootstrap Confidence Intervals | One-Shot: aib_audit() | Formal Definition of Bias Amplification | Summary of Core Estimands

Overview | Installation | Step 1: Build the Design Robustness Index | From design type labels | From continuous sub-scores | Step 2: Fit the DR-Meta Model | Compare exponential vs linear variance function | Step 3: Visualise | Forest plot | Variance function | Weight vs DR (Lemma 3) | Step 4: Heterogeneity Decomposition (Proposition 6) | Step 5: Influence Diagnostics (LOO) | Step 6: Publication Bias | Connection to the Literature | References

Overview | 1. Simulating data | 2. Longitudinal pooling: ml_meta() | 3. Sensitivity analysis: ml_sens() | 4. Nonlinear time trend: ml_spline() | 5. Combined figure: ml_plot() | 6. Benchmark calibration: ml_benchmark() | 7. Fragility analysis: ml_fragility() | 8. Accessing stored fits | References

Overview | The confoundsens object | Robustness curve | Sensitivity contour plot | Sensitivity Love plot | Local Taylor diagnostic | Fitting a local quadratic | Simulating curvature regimes | References

What is a cross-level interaction? | Setup | Centering strategy for cross-level interactions | Fit the random-slopes model | Probe simple slopes | Johnson–Neyman region | Visualise | Full summary for reporting | Reporting guidance | Assumptions to check

Overview | The built-in dataset | Step 1: Center variables | Step 2: Fit the model | Step 3: Probe simple slopes | Step 4: Johnson–Neyman interval | Step 5: Plot the interaction | Step 6: Full summary report | Tips

Why nonlinear causal effects? | Installation | Quick start | 1. Simulate data with a threshold effect | 2. Fit with IPW | 3. Fit with G-computation | 4. Check overlap (positivity) | Comparing DGPs | Choosing degrees of freedom | Methods summary | References

Overview | Installation | Quickstart: Simulated Data | Fitting the Model | Summarizing Results | Visualizing the Gap Trajectory | Hypothesis Testing | Comparing to Separate Splines | Non-Monotone Gap Example | Running a Benchmark Simulation | Using Your Own Data | Session Info