Introduction | Data Format | Why there is a lineup_member column | 1. Calibration Analysis | Basic Calibration | Interpreting the Calibration Plot | Calibration by Condition | 2. Bayesian Information-Gain Analysis | The arithmetic, briefly | Prior-Posterior Curves | Information Gain | Confidence-Based Bayesian Analysis | Base-Rate Equivalency of Evidence (BREE) | 3. Expected Utility Analysis | Define Utility Matrix | Compute Utility Curves | Compare Procedures | Sensitivity to Base Rate | 4. Deviation from Perfect Performance (DPP) | Basic DPP | Different costs and base rates | Compare DPP Between Groups | When to Use DPP | 5. ANRI: Adjusted Normalized Resolution Index | Basic ANRI | Bootstrap Confidence Intervals | Compare Groups | When to Use ANRI vs NRI | Integrating Multiple Methods | Reporting Results | Example Write-Up | References | Session Info

Introduction | Signal Detection Theory, briefly | Decision rules | The criterion, in plainer terms | Basic Data Simulation | Power Analysis | What the function does | A worked power analysis | Plotting, and adjusting the plot | Method Check: Sensitivity to d′ | Comparing Experimental Designs | Integration with r4lineups Analyses | ROC Analysis | CAC Analysis | RAC Analysis | Full ROC Analysis | Choosing Parameter Values | Summary | References | Further Reading

Overview | Where the methods come from | A caution about what d′ means for a lineup | Summary metrics from counts | Variance estimation | Comparing two conditions | Notes | The compound-model alternative | What it needs, and why you may not have it | A worked example | Comparing conditions | Which to use | Technical Details | The estimators | Variance, and why there are three methods | The extreme-rate correction | Assumptions | References | Further Reading

Introduction | What is an ROC curve? | Discriminability and criterion | Why lineup ROCs are hard | From AUC to pAUC | Critical commentary: pAUC is contested | The region problem | The deeper objection | What the curve leaves out | Key articles | The statistical framework | What the test actually is | Why bootstrap the standard error? | Is normality reasonable? | A worked comparison | Specifying the region explicitly | How many bootstrap resamples? | Multiple comparisons | Power | Technical Details | How pAUC is computed | How the standard error is obtained | Assumptions | Effect size | Summary | References | Further Reading

Purpose | If you have only used frequentist methods | Data Shapes | Effective Size | Functional Size | Diagnosticity Ratio | Calibration | SDT d' Comparison | Workflow Position | Technical Details | What is being sampled | The prior | Monte Carlo error | Assumptions | References | Further Reading

Introduction | The Three Models | 2-HT Model: Latent Cognitive Processes | EIG: Information-Theoretic Measure | Full ROC: Investigator Discriminability | Basic Model Comparison | Loading Data | Comparing All Models | Detailed Summary | Visualizing Model Comparisons | Individual Model Access | 2-HT Model Results | EIG Results | Full ROC Results | Method-Choice Guidance | When to Use Each Model | Comparing Model Fits | Advanced Usage | Fitting Specific Models Only | Using Confidence Bins | Custom Prior for EIG | Simulated Data Example | Comparing Models with Known Parameters | Sensitivity to the Generating d′ | Practical Examples | Example 1: Evaluating a Lineup Procedure | Example 2: Identifying Sources of Bias | Example 3: Comparing Detection vs. Guessing | Formatted Comparison Tables | Console Format | Markdown Format | Interpretation Guidelines | Common Pitfalls | 1. Insufficient Sample Size | 2. Model Convergence Issues | 3. Comparing Non-Comparable Measures | Best Practices | 1. Fit Multiple Models | 2. Report All Model Results | 3. Check Model Assumptions | Technical Details | What each model estimates, and on what scale | 2-HT estimation | EIG | Full ROC | Assumptions common to all three | Summary | References | Further Reading

Introduction | Why measure face similarity? | An important caution before going further | What This Vignette Covers | Setup | Check Current Setup | Install Python Dependencies | If the Python setup defeats you | Verify Installation | Basic Face Comparison | Compare Two Faces | Understanding the Output | Lineup Similarity Analysis | Analyze Complete Lineup | Examining Results | Describing the similarity profile | Models and Metrics | Available Models | Distance Metrics | Comparing Models | Visualization | Display Lineup with Similarity Scores | Similarity Heatmap | Similarity Distribution | Advanced Features | Extract Face Embeddings | Dimensionality Reduction Visualization | Batch Processing Multiple Lineups | Integration with Traditional Measures | Compare with Effective Size | Similarity and mock-witness choices: a hypothesis to test | Validation Studies | Practical Guidelines | Interpreting Similarity Scores | Best Practices | Troubleshooting | Example Workflow | References | Technical Details | What is computed | Assumptions and limitations | Reproducibility | Session Info

What these models are | Why it is important to know which one is right | What this interface does and does not cover | Installing the engine | Preparing data | Fitting | Can the fit tell the generating rules apart? | Interpreting the output | Technical Details | How the models are estimated | Why AIC and BIC are NA | What to check before interpreting | Assumptions | References | Further Reading

Introduction | Every response, not just suspect identifications | Why the partial ROC curve does not span the full range | The key idea: two signal detection tasks | Basic usage | Data structure | Compute a full ROC | Ordering methods, and a warning about the default | A-priori ordering | Diagnosticity ordering | How large is the bias? | Binning confidence | Understanding the output | The diagnosticity table | The ROC data | Interpreting the AUC | Comparing procedures | Technical Details | How the curve is built | Edge cases | Assumptions | No standard errors | Summary | References | Further Reading

Introduction | 1. Expected Information Gain (EIG) | In plain terms | The arithmetic | Response-level information gain | Plots | 2. PPV-range estimation | When the three coincide, and why | When they diverge | Interpretation guidance | Technical Details | EIG | PPV range | Assumptions | References | Further Reading

Overview | What mSDT offers over ordinary SDT | Joint distributions, and whether fillers are independent | Max filler distribution | Moments | Estimating mSDT parameters from rejection rates | Why rejection rates in particular | What the helper does | What this estimator gives up | Joint distribution plots | Technical Details | What is computed | Assumptions | References | Further Reading

Overview | The indices | A published example | Interpreting d'(IFa) as lineup bias | Trial-level data, bootstrap intervals and confidence | Comparing two conditions | Cautions | References | Further Reading

Data Format | Null foils, and why table() can mislead | A larger dataset | r4lineups Sample Datasets | Lineup Proportion | Calculating proportion for a single target/lineup member | Compute bootstrapped estimates | Comparing against a normal-theory interval | Calculating proportion for each lineup member | Visualising the bootstrap distribution | Functional Size | Effective Size | 1. Malpass's original (1981) and adjusted effective size (see: Tredoux, 1998) | Compute bootstrapped estimates (Malpass's adjusted) | Compute bootstrap descriptive statistics | 2. Tredoux's measure of Effective Size, E' | E' has small-sample bias, downward for fair lineups | Getting the choice distribution without mock witnesses | 3. Effective Size Per Foils | Comparing two effective sizes | Diagnosticity Ratio | Differences between Independent Diagnosticity Ratios | Homogeneity using normal theory estimates | A cautionary case: why you must not pool when Q is significant | Homogeneity with bootstrapped confidence intervals | ROC Analysis (Confidence ~ Accuracy) | Data format for ROC analysis | Computing and plotting the ROC | Full ROC curves | Similarity of Faces in a Lineup | Technical Details | The measures, and what each assumes | Nominal, adjusted and effective size | Inference | Assumptions common to the fairness measures | Other vignettes

Introduction | Why response time? | The 10-to-12-second rule, and what happened to it | Setup | Simulating Data with Response Times | Response Time and Accuracy: the simplest analysis | Basic RAC Analysis | Choosing time bins | Compute and plot | RAC and CAC Compared | Fine-Grained Analysis | A continuous alternative to binning | Estimating a time boundary | Comparing Conditions | Custom Analysis | Technical Details | How RAC is computed | Standard errors | Using RAC with Real Data | Exporting Results | Summary | References

Overview | What changes when you move from classic SDT to a GLM | Why a probit regression gives you d′ | Simulated data | Single-level GLM | Multilevel GLMM | Participants, items, or both | The estimates move too, and predictably | Including covariates | Technical Details | What is estimated | Coding conventions | Assumptions | A limitation | References | Further Reading

Introduction | The general approach | The four parameters | Data format | 1. Fit the model using counts | 2. Model diagnostics and plots | 3. Bootstrap confidence intervals | 4. What b tells you about lineup fairness | Does it work? | A caution that comes with it | Technical Details | Estimation | Identifiability | Confidence intervals | Assumptions | References | Further Reading