Package index • r4lineups

Data preparation and validation

Validate, standardize, and simulate lineup data.

classify_lineup_choices(): Classify Raw Lineup Choices into Identification Outcomes
create_example_lineup_data(): Create Example Lineup Data
datacheck1(): Helper function
datacheck2(): Helper function
datacheck3(): Helper function
line73: line73
lineup_example: Example Lineup Identification Data
lineup_table(): Tabulate Lineup Choices, Including Null Foils
mickwick: Confidence & Accuracy data (Mickes & Wixted)
mockdata: mockdata
nortje2012: nortje2012
plot(<power_analysis>): Plot Power Analysis Results
print(<lineup_data>): Print Method for Lineup Data
print(<lineup_table>): Print Method for lineup_table Objects
simulate_lineup_data(): Simulate Lineup Identification Data
simulate_power_analysis(): Simulate Power Analysis for Lineup Studies
standardize_lineup_data(): Standardize Lineup Identification Data
validate_lineup_data(): Validate Lineup Identification Data

Lineup bias and member proportions

Proportions choosing each lineup member, foil bias, and bootstrap CIs.

allfoil_cihigh(): Confidence Intervals for Proportion
allfoilbias(): Bias for each lineup member
allprop(): Lineup proportion for all lineup members
gen_boot_propci(): Percentile of Bootstrapped Lineup Proportion
gen_boot_propmean_se(): Descriptive statistics for bootstrapped lineup proportion
gen_boot_samples(): Bootstrap resampling
gen_boot_samples_list(): Bootstrapped resampling
lineup_boot_allprop(): Confidence intervals for lineup proportion
lineup_prop_boot(): Bootstrapped lineup proportion
lineup_prop_tab(): Lineup proportion
lineup_prop_vec(): Lineup proportion
makevec_prop(): Helper functions
rot_vector(): Rotate vector

Effective size

Tredoux’s E’, Malpass’s effective size, and inference on them.

compare_eff_sizes.boot(): Comparing Effective Size: Base function for bootstrapping
esize_boot_dist(): Bootstrap Distribution of Effective Size
esize_m(): Effective Size
esize_m_boot(): Bootstrapped Effective Size
esize_T(): Effective Size (Tredoux, 1998)
esize_T_bayes(): Bayesian Posterior Distribution of Effective Size (Tredoux, 1998)
esize_T_bayes_compare(): Bayesian Comparison of Effective Size (Tredoux, 1998) Across Two Lineups
esize_T_boot(): Bootstrapped Effective Size (Tredoux, 1998)
esize_T_ci_n(): Effective Size with Confidence Intervals from Normal Theory (Tredoux, 1998)
i_esize_T(): I Component of Effective Size (Tredoux, 1998)

Functional size

Functional size estimation and bootstrap/Bayesian inference.

func_size(): Functional Size
func_size_bayes(): Bayesian Functional Size (Beta-Binomial Model)
func_size_report(): Functional Size with Bootstrapped Confidence Intervals
func_size.boot(): Bootstrapped Functional Size

Diagnosticity

Diagnosticity ratios and homogeneity tests.

chi_diag(): Chi-squared estimate of homogeneity of diagnosticity ratio
d_bar(): Mean diagnosticity ratio for k lineup pairs
d_weights(): Diagnosticity ratio weights
diag_param(): Parameters for diagnosticity ratio
diag_ratio_T(): Diagnosticity Ratio (Tredoux, 1998)
diag_ratio_T_bayes(): Bayesian Diagnosticity Ratio (Tredoux, Beta-Binomial Model)
diag_ratio_T_bayes_compare(): Bayesian Comparison of Two Diagnosticity Ratios
diag_ratio_W(): Diagnosticity Ratio (Wells & Lindsay, 1980; Wells & Turtle, 1986)
homog_diag(): Master function: Homogeneity of diagnosticity ratio
homog_diag_boot(): Homogeneity of diagnosticity ratio with bootstrapped CIs
ln_diag_ratio(): Ln of Diagnosticity Ratio
var_diag_ratio(): Asymptotic Variance of Log Diagnosticity
var_lnd(): Variance of ln of diagnosticity ratio

ROC, CAC, and RAC analysis

Receiver operating characteristic, confidence-accuracy, and response time-accuracy analysis.

make_cac(): Compute and Plot CAC for Lineup Identification
make_cac_gg(): Plot CAC Curve
make_cacdata(): Compute CAC (Confidence-Accuracy Characteristic) Data
make_rac(): Compute and Plot RAC for Lineup Identification
make_rac_gg(): Plot RAC Curve
make_racdata(): Compute RAC (Response Time-Accuracy Characteristic) Data
make_roc(): Compute and Plot ROC Curve for Lineup Identification
make_roc_gg(): Plot ROC Curve for Lineup Identification
make_rocdata(): Compute ROC Data for Lineup Identification
plot(<lineup_roc_data>) plot(<lineup_roc>) plot(<lineup_cac_data>) plot(<lineup_cac>) plot(<lineup_fullroc_data>) plot(<lineup_fullroc>): Plot Methods for ROC and CAC Objects
print(<lineup_cac>): Print Method for lineup_cac Objects
print(<lineup_rac>): Print Method for lineup_rac Objects
print(<lineup_roc>): Print Method for lineup_roc Objects

Full ROC (Smith & Yang, 2020)

Full ROC curves using all response categories.

make_fullroc(): Compute and Plot Full ROC Curve (Smith & Yang, 2020)
make_fullroc_data(): Compute Full ROC Data for Lineup Identification (Smith & Yang, 2020)
plot_fullroc(): Plot Full ROC Curve
print(<lineup_fullroc>): Print Method for lineup_fullroc Objects

pAUC and DPP comparisons

Statistical comparison of ROC curves and deviation from perfect performance.

compare_dpp(): Compare DPP Between Two Procedures
compare_pauc(): Compare pAUC Between Two ROC Curves
compute_dpp(): Compute and Plot DPP
make_dpp(): Compute Deviation from Perfect Performance (DPP)
plot_dpp(): Plot DPP Across Operating Points
plot_dpp_comparison(): Plot DPP Comparison Between Two Procedures
plot(<pauc_comparison>): Plot pAUC Comparison
print(<lineup_dpp>): Print Method for lineup_dpp Objects
print(<lineup_dpp_comparison>): Print Method for lineup_dpp_comparison Objects
print(<pauc_comparison>): Print Method for pauc_comparison Objects
summary(<pauc_comparison>): Summary Method for pauc_comparison Objects

Expected information gain and PPV

EIG (Starns et al., 2023) and positive predictive value ranges.

compute_eig(): Compute Expected Information Gain (EIG)
innocent_id_rate_effective(): Compute Innocent Suspect ID Rate with Effective Size Correction
innocent_id_rate_nominal(): Compute Innocent Suspect ID Rate with Nominal Size Correction
innocent_id_rate_uncorrected(): Compute Innocent Suspect ID Rate with No Correction
make_eig(): Main Function to Compute and Visualize EIG
make_eig_data(): Prepare EIG Data from Lineup Identification
make_ppv_range(): Main Function to Compute and Visualize PPV Range
plot_eig(): Plot Information Gain by Response Category
plot_eig_posteriors(): Plot Posterior Probabilities for Response Categories
plot_ppv_range(): Plot PPV Range Across Confidence Levels
ppv_by_confidence(): Compute PPV by Confidence with Lineup Size Correction
ppv_range_by_confidence(): Compute PPV Range by Confidence (All Three Corrections)
print(<lineup_eig>): Print Method for lineup_eig Objects
print(<lineup_ppv>): Print Method for lineup_ppv Objects
print(<lineup_ppv_range>): Print Method for lineup_ppv_range Objects
summary(<lineup_eig>): Summary Method for lineup_eig Objects

Calibration and ANRI

Confidence-accuracy calibration, over/underconfidence, and adjusted normalized resolution index.

bootstrap_anri(): Bootstrap Confidence Intervals for ANRI
calibration_bayes(): Bayesian Calibration Analysis (Beta-Binomial Model)
compare_anri(): Compare ANRI Between Groups with Bootstrap
compute_anri(): Compute ANRI (Adjusted Normalized Resolution Index)
make_calibration(): Compute and Plot Calibration for Lineup Identification
make_calibration_by_condition(): Compute Calibration Statistics by Condition
make_calibration_by_condition_gg(): Plot Calibration Curves by Condition
make_calibration_data(): Compute Calibration Statistics for Eyewitness Identification
make_calibration_gg(): Plot Calibration Curve
plot_anri_comparison(): Plot ANRI Comparison Between Groups
plot_anri_difference_distribution(): Plot Bootstrap Distribution of ANRI Difference
print(<lineup_anri>): Print Method for ANRI Objects
print(<lineup_anri_comparison>): Print Method for ANRI Comparison Objects
print(<lineup_calibration>): Print Method for lineup_calibration Objects

Bayesian curves, utility, and BREE

Prior-posterior curves, expected utility analysis, and base-rate effect-equivalency.

compare_utility(): Compare Utilities for Two Procedures
make_bayes_curves(): Compute Bayesian Prior-Posterior and Information Gain Curves
make_bree_curve(): Compute Base-Rate Effect-Equivalency (BREE) Curves
make_utility_curves(): Compute Expected Utility Curves for Lineup Identification
make_utility_difference(): Compute Utility Difference Curves Comparing Two Procedures
plot_bayes_information_gain(): Plot Information Gain Curves
plot_bayes_prior_posterior(): Plot Prior-Posterior Curves
plot_bree(): Plot BREE Curve
plot_utility_curves(): Plot Expected Utility Curves
plot_utility_difference(): Plot Utility Difference Curve
print(<lineup_bayes_curves>): Print Method for Bayes Curves Objects
print(<lineup_utility_comparison>): Print Method for lineup_utility_comparison Objects

Winter 2-HT model

Two-high-threshold multinomial processing tree model (Winter et al., 2022).

boot_winter_2ht(): Bootstrap Confidence Intervals for 2-HT Model Parameters
fit_winter_2ht(): Winter et al. (2022) Two-High Threshold (2-HT) MPT Model for Eyewitness Identification
plot_2ht_fit(): Plot Observed vs. Expected Counts
plot_2ht_parameters(): Plot Parameter Estimates from 2-HT Model
plot(<winter_2ht>): Plot Method for winter_2ht Objects
plot(<winter_2ht_boot>): Plot Bootstrap Distributions
print(<winter_2ht>): Print Method for winter_2ht Objects
print(<winter_2ht_boot>): Print Method for winter_2ht_boot Objects
summary(<winter_2ht>): Summary Method for winter_2ht Objects
summary(<winter_2ht_boot>): Summary Method for winter_2ht_boot Objects

mSDT and MAX SDT models

Multi-item signal detection theory and compound-decision MAX SDT fitting.

compare_max_sdt(): Compare Two Nested MAX SDT Models
dmax_filler() pmax_filler() qmax_filler() rmax_filler(): mSDT: Max Filler Distribution (IID Normal Fillers)
estimate_msdt_params() msdt_gamma_from_rej() msdt_dprime_from_rej(): mSDT Parameter Estimation from Rejection Rates
fit_max_sdt(): Restricted Independent-Observations/MAX Model for Lineup Counts
max_filler_moments(): Max Filler Distribution Moments
plot_msdt_joint(): Plot mSDT Joint Distributions

Multi-d’ model (Lee & Penrod)

Multiple empirical d’ indices from the full TP/TA response table, including resultant lineup-bias indices.

compare_multid(): Compare Multi-d' Indices Between Two Conditions
make_multid(): Multi-d' Model of Lineup Performance (Lee & Penrod, 2019)
plot(<multid>): Plot a Multi-d' Analysis

Wixted lineup-memory models (optional pyWitness engine)

Fit and compare Independent Observations, Ensemble, and Integration models for fair simultaneous lineups.

check_pywitness_deps(): Check Availability of the pyWitness Engine
fit_lineup_models(): Fit Competing Wixted Lineup-Memory Models
install_pywitness(): Install the Audited pyWitness Engine
plot(<lineup_model_comparison>): Plot a Wixted Lineup-Memory Model Comparison

SDT estimation and comparison

SDT parameters from ROC data, GLM/GLMM estimation, and summary-count comparisons.

compare_sdt_summary(): Compare SDT Summary Metrics Between Two Conditions
extract_sdt_metrics(): Extract SDT Metrics from a GLM/GLMM
fit_sdt_glm(): Fit an SDT GLM for Old/New Recognition
fit_sdt_glmm(): Fit an SDT GLMM for Old/New Recognition
fit_sdt_roc(): Fit Signal Detection Theory Model to ROC Data
plot(<sdt_roc_fit>): Plot Method for SDT ROC Fit
print(<sdt_roc_fit>): Print Method for SDT ROC Fit
sdt_compare(): Bayesian Comparison of SDT Sensitivity (d') Between Two Conditions
sdt_summary_from_counts(): SDT Summary Statistics from Counts
sdt_summary_variance(): Variance Estimates for SDT Summary Metrics
summary(<sdt_roc_fit>): Summary Method for SDT ROC Fit

Model comparison

Unified comparison of 2-HT, EIG, and full ROC models.

compare_models(): Compare Multiple Models for Lineup Identification Data
format_comparison_table(): Create Comprehensive Model Comparison Table
plot(<model_comparison>): Plot Side-by-Side Model Comparisons
print(<model_comparison>): Print Method for model_comparison Objects
summary(<model_comparison>): Summary Method for model_comparison Objects

Face similarity (Python/deepface)

Deep-learning face similarity, embeddings, and landmarks (requires optional Python setup).

available_detectors(): List Available Face Detectors
available_models(): List Available Face Recognition Models
batch_embeddings(): Extract Embeddings for Multiple Images
check_python_deps(): Check Python Dependencies
cosine_to_similarity(): Convert Cosine Distance to Similarity Score
detect_faces(): Detect Faces in an Image
display_lineup(): Display Lineup as Image Grid
embedding_distance(): Compute Distance Between Two Embeddings
face_similarity(): Compute Face Similarity Between Two Images
get_embedding(): Extract Face Embedding from an Image
get_face_landmarks(): Get 478-Point Face Mesh Landmarks
get_key_landmarks(): Get Key Facial Landmarks (5-Point)
has_valid_face(): Check if Image Contains a Valid Face
install_r4lineups_python(): Install Python Dependencies for r4lineups
lineup_similarity(): Compute Lineup Similarity Matrix
plot_embedding_space(): Plot Embedding Space
plot_lineup_bias_distribution(): Plot Bootstrap Distribution of Lineup Bias
plot_lineup_similarity(): Plot Lineup Similarity Results
plot_similarity_distribution(): Plot Similarity Distribution
print(<lineup_similarity>): Print Method for lineup_similarity
summary(<lineup_similarity>): Summary Method for lineup_similarity

Shiny app

Interactive Shiny interface.

run_r4lineups_app(): Run the r4lineups Shiny app

Other helpers

Additional helper functions.

eff_size_per_foils(): Effective Size per Foils
effsize_compare(): Master Function: Comparing Effective Size
gen_esize_m(): Effective Size (across a dataframe)
gen_esize_m_ci(): Bootstrap Quantile for Effective Size
gen_lineup_prop(): Lineup proportion over dataframe
gen_linevec(): Lineup vector
lineup_bias_boot_dist(): Bootstrap Distribution of Lineup Bias (Target Proportion)
lineup_pairwise_matrix(): Compute Pairwise Similarity Matrix for All Lineup Members
plot_effective_size_conf(): Plot Effective Size by Confidence Level
plot_error_rate_conf(): Plot Error Rate by Confidence Level
plot_esize_distribution(): Plot Bootstrap Distribution of Effective Size
plot(<esize_T_bayes>): Plot method for esize_T_bayes objects
plot(<esize_T_bayes_compare>): Plot method for esize_T_bayes_compare objects
print(<esize_T_bayes>): Print method for esize_T_bayes objects
print(<esize_T_bayes_compare>): Print method for esize_T_bayes_compare objects
print(<simulated_lineup_data>): Print Method for Simulated Lineup Data
rep_index(): Rep index