Package index • forestsearch

Core Algorithm

Main forestsearch function and subgroup search engine.

forestsearch(): ForestSearch: Exploratory Subgroup Identification
print(<forestsearch>): Print Method for forestsearch Objects
summary(<forestsearch>): Summary Method for forestsearch Objects
subgroup.search(): Subgroup Search for Treatment Effect Heterogeneity (Improved, Parallelized)
get_FSdata(): ForestSearch Data Preparation and Feature Selection

Subgroup Evaluation & Selection

Functions for evaluating, sorting, and selecting candidate subgroups.

analyze_subgroup(): Analyze subgroup for summary table (OPTIMIZED)
assign_subgroup_membership(): Assign data to subgroups based on selected node
evaluate_subgroup_consistency(): Evaluate Single Subgroup for Consistency (Fixed-Sample)
extract_subgroup(): Extract Subgroup Information
get_subgroup_membership(): Get subgroup membership vector
prepare_subgroup_data(): Prepare subgroup data for analysis
select_best_subgroup(): Select best subgroup based on criterion
sort_subgroups(): Sort Subgroups by Focus
sort_subgroups_preview(): Sort Subgroups by Focus at consistency stage (consistency not available at this point)
remove_near_duplicate_subgroups(): Remove Near-Duplicate Subgroups
remove_redundant_subgroups(): Remove Redundant Subgroups

Consistency Evaluation

Split-sample consistency evaluation including the two-stage sequential method.

subgroup.consistency(): Evaluate Subgroup Consistency
evaluate_consistency_twostage(): Evaluate Consistency (Two-Stage Algorithm)
run_single_consistency_split(): Run Single Consistency Split
setup_parallel_SGcons(): Set up parallel processing for subgroup consistency
sg_consistency_out(): Output Subgroup Consistency Results
wilson_ci(): Wilson Score Confidence Interval
early_stop_decision(): Early Stopping Decision

Bootstrap Bias Correction

Bootstrap methods for bias-corrected hazard ratio estimation using infinitesimal jackknife variance estimation (Leon et al., 2024).

forestsearch_bootstrap_dofuture(): ForestSearch Bootstrap with doFuture Parallelization
bootstrap_results(): Bootstrap Results for ForestSearch with Bias Correction
bootstrap_ystar(): Bootstrap Ystar Matrix
count_boot_id(): Count ID Occurrences in Bootstrap Sample
generate_bootstrap_synthetic(): Generate Synthetic Data using Bootstrap with Perturbation
generate_bootstrap_with_noise(): Generate Bootstrap Sample with Added Noise
generate_gbsg_bootstrap_general(): Generate Synthetic GBSG Data using Generalized Bootstrap
get_dfRes(): Bootstrap Confidence Interval and Bias Correction Results

Bootstrap Summaries

Summarizing and formatting bootstrap results into publication-ready tables and diagnostics.

summarize_bootstrap_results(): Enhanced Bootstrap Results Summary
summarize_bootstrap_subgroups(): Summarize Bootstrap Subgroup Analysis Results
summarize_bootstrap_events(): Summarize Bootstrap Event Counts
summarize_factor_presence_robust(): Summarize Factor Presence Across Bootstrap Subgroups
format_bootstrap_table(): Format Bootstrap Results Table with gt
format_bootstrap_diagnostics_table(): Format Bootstrap Diagnostics Table with gt
format_bootstrap_timing_table(): Format Bootstrap Timing Table with gt
format_subgroup_summary_tables(): Format Subgroup Summary Tables with gt
create_factor_summary_tables(): Create Factor Summary Tables from Bootstrap Results

Cross-Validation

K-fold and repeated cross-validation for assessing subgroup identification stability and agreement metrics.

forestsearch_Kfold(): ForestSearch K-Fold Cross-Validation
forestsearch_tenfold(): ForestSearch Repeated K-Fold Cross-Validation
forestsearch_KfoldOut(): ForestSearch K-Fold Cross-Validation Output Summary
CV_sgs(): Cross-Validation Subgroup Match Summary
cv_summary_tables(): Create Summary Tables from forestsearch_KfoldOut Results
cv_metrics_tables(): Create Metrics Tables for Cross-Validation Results
cv_summary_text(): Create Compact CV Summary Text
cv_compare_results(): Compare Multiple CV Results
print(<fs_kfold>): Print Method for K-Fold CV Results
print(<fs_tenfold>): Print Method for Repeated K-Fold CV Results

GRF Integration

Generalized Random Forest methods for heterogeneous treatment effect estimation and variable importance screening.

grf.subg.harm.survival(): GRF Subgroup Identification for Survival Data
grf.subg.eval(): GRF Subgroup Evaluation and Performance Metrics
fit_causal_forest(): Fit causal survival forest
fit_policy_trees(): Fit policy trees up to specified depth
create_grf_config(): Helper Functions for GRF Subgroup Analysis
validate_grf_data(): Validate input data for GRF analysis
print_grf_details(): Print detailed output for debugging
compute_node_metrics(): Compute node metrics for a policy tree
find_leaf_split(): Find the split that leads to a specific leaf node

Cox Model Utilities

Cox proportional hazards model wrappers with robust standard errors, spline fitting, and average hazard ratio calculations.

cox_summary(): Cox model summary for subgroup (OPTIMIZED)
cox_summary_batch(): Batch Cox summaries with caching
cox_summary_legacy(): Cox model summary for subgroup
cox_summary_vectorized(): Cox model summary for subgroup - vectorized version
cox_ahr_cde_analysis(): Comprehensive Wrapper for Cox Spline Analysis with AHR and CDE Plotting
print(<cox_ahr_cde>): Print method for cox_ahr_cde objects
summary(<cox_ahr_cde>): Summary method for cox_ahr_cde objects
cox_cs_fit(): Fit Cox Model with Cubic Spline for Treatment Effect Heterogeneity
build_cox_formula(): Build Cox Model Formula
fit_cox_models(): Fit Cox Models for Subgroups
get_Cox_sg(): Fit Cox Model for Subgroup
get_split_hr_fast(): Fast Cox Model HR Estimation
rmst_calculation(): RMST calculation for subgroup

Subgroup Tables & Estimates

Formatted tables of subgroup estimates and labels.

sg_tables(): Enhanced Subgroup Summary Tables (gt output)
SG_tab_estimates(): Subgroup summary table estimates
SGplot_estimates(): Violin/Boxplot Visualization of HR Estimates
FS_labels(): Convert Factor Code to Label
create_summary_table(): Create Enhanced Summary Table for Baseline Characteristics
create_summary_table_compact(): Preset: Compact Table
create_summary_table_minimal(): Preset: Minimal Table (No Highlighting, No Alternating)
create_summary_table_presentation(): Preset: Presentation Table (Large Fonts)
create_summary_table_publication(): Preset: Publication-Ready Table
create_sample_size_table(): Create Sample Size Table for Multiple Scenarios

Visualization

Publication-ready plotting functions for forest plots, survival curves, and subgroup characteristics.

gg_forest(): ggplot2 / patchwork forest plot
plot_subgroup_results_forestplot(): Plot Subgroup Results Forest Plot
render_forestplot(): Render ForestSearch Forest Plot
save_forestplot(): Save ForestSearch Forest Plot to File
create_forest_theme(): Create Forest Plot Theme with Size Controls
print(<fs_forest_theme>): Print Method for ForestSearch Forest Theme
print(<fs_forestplot>): Print Method for ForestSearch Forest Plot
plot(<fs_forestplot>): Plot Method for ForestSearch Forest Plot
create_subgroup_summary_df(): Create Subgroup Summary Data Frame for Forest Plot
plot_km_band_forestsearch(): Plot Kaplan-Meier Survival Difference Bands for ForestSearch Subgroups
quick_km_band_plot(): Quick Plot KM Bands from ForestSearch
plot_sg_results(): Plot ForestSearch Subgroup Results
plot_sg_weighted_km(): Plot Weighted Kaplan-Meier Curves for ForestSearch Subgroups
print(<fs_weighted_km>): Print Method for fs_weighted_km Objects
plot_subgroup(): Plot Subgroup Survival Curves
plot(<fs_sg_plot>): Plot Method for fs_sg_plot Objects
print(<fs_sg_plot>): Print Method for fs_sg_plot Objects
plot_subgroup_effects(): Plot Subgroup Analysis Results
plot(<forestsearch>): Plot ForestSearch Results
plot_spline_treatment_effect(): Plot Spline Treatment Effect Function
plot_detection_curve(): Plot Detection Probability Curve
compare_detection_curves(): Compare Detection Curves Across Sample Sizes
sens_text(): Generate Cross-Validation Sensitivity Text
figure_note(): Generate Figure Note for Quarto/RMarkdown
km_summary(): KM median summary for subgroup

Data Preparation & Encoding

Cut point generation, dummy variable creation, and variable selection.

get_dfpred(): Generate Prediction Dataset with Subgroup Treatment Recommendation
dummy_encode(): Dummy-code a data frame (numeric pass-through, factors expanded)
add_id_column(): Add ID Column to Data Frame
evaluate_comparison(): Evaluate a Comparison Expression Without eval(parse())
evaluate_cuts_once(): Cache and validate cut expressions efficiently
detect_variable_types(): Automatically Detect Variable Types in a Dataset
is_flag_continuous(): Check if cut expression is for a continuous variable (OPTIMIZED)
is_flag_drop(): Check if cut expression should be dropped
is.continuous(): Check if a variable is continuous
get_cut_name(): Get variable name from cut expression
cut_var(): Generate cut expressions for a variable
lasso_selection(): LASSO selection for Cox model
filter_by_lassokeep(): Filter a vector by LASSO-selected variables

Tree Cut Extraction

Extract and process cut points from tree-based models.

extract_all_tree_cuts(): Extract all cuts from fitted trees
extract_selected_tree_cuts(): Extract cuts from selected tree only
extract_tree_cuts(): Extract cut information from a policy tree
extract_idx_flagredundancy(): Extract redundancy flag for subgroup combinations

Data Generating Mechanisms

Functions for creating data generating mechanisms (DGMs) for simulation studies with configurable treatment effect heterogeneity.

generate_aft_dgm_flex(): Generate Synthetic Survival Data using AFT Model with Flexible Subgroups
create_gbsg_dgm(): Create GBSG-Based AFT Data Generating Mechanism
print(<gbsg_dgm>): Print Method for gbsg_dgm Objects
compute_dgm_cde(): Compute and Attach CDE Values to a DGM Object
create_dgm_for_mrct(): Create Data Generating Mechanism for MRCT Simulations
simulate_from_dgm(): Simulate Survival Data from AFT Data Generating Mechanism
simulate_from_gbsg_dgm(): Simulate Trial Data from GBSG DGM
get_dgm_with_output(): Create DGM with Output File Path
calibrate_cens_adjust(): Calibrate Censoring Adjustment to Match DGM Reference Distribution
check_censoring_dgm(): Diagnose Censoring Consistency Between DGM Source Data and Simulated Data
calibrate_k_inter(): Calibrate k_inter for Target Subgroup Hazard Ratio
find_k_inter_for_target_hr(): Find k_inter Value to Achieve Target Harm Subgroup Hazard Ratio
validate_k_inter_effect(): Validate k_inter Effect on HR Heterogeneity
sensitivity_analysis_k_inter(): Sensitivity Analysis of Hazard Ratios to k_inter

Simulation Studies

Running and summarizing simulation studies for operating characteristics.

run_simulation_analysis(): Run Single Simulation Analysis
default_fs_params(): Default ForestSearch Parameters for GBSG Simulations
default_grf_params(): Default GRF Parameters for GBSG Simulations
summarize_simulation_results(): Summarize Simulation Results
format_oc_results(): Format Operating Characteristics Results as GT Table
build_classification_table(): Build Classification Rate Table from Simulation Results
build_estimation_table(): Build Estimation Properties Table from Simulation Results
interpret_estimation_table(): Generate Narrative Interpretation of Estimation Properties
render_reference_table(): Render Reference Simulation Table as gt
compute_detection_probability(): Compute Probability of Detecting True Subgroup
generate_detection_curve(): Generate Detection Probability Curve
find_required_sample_size(): Find Minimum Sample Size for Target Detection Power
create_null_result(): Create result object when no subgroup is found
create_success_result(): Create result object for successful subgroup identification

Multi-Regional Clinical Trials

Specialized functions for multi-regional clinical trial (MRCT) subgroup analysis with regional consistency evaluation.

mrct_region_sims(): MRCT Regional Subgroup Simulation
summaryout_mrct(): Summary Tables for MRCT Simulation Results
validate_mrct_data(): Validate Dataset for MRCT Simulations

Formatting & Estimation Helpers

Formatting utilities, confidence intervals, and estimation helpers.

format_CI(): Format Confidence Interval for Estimates
format_results(): Format results for subgroup summary
hrCI_format(): Format Hazard Ratio and Confidence Interval
n_pcnt(): Calculate n and percent
ci_est(): Confidence Interval for Estimate
calc_cov(): Calculate Covariance for Bootstrap Estimates
get_targetEst(): Target Estimate and Standard Error for Bootstrap
calculate_counts(): Calculate counts for subgroup summary
calculate_potential_hr(): Calculate potential outcome hazard ratio
density_threshold_both(): Bivariate Density for Split-Sample HR Threshold Detection
find_quantile_for_proportion(): Find Quantile for Target Subgroup Proportion
qlow(): 25th Percentile (Quantile Low)
qhigh(): 75th Percentile (Quantile High)
get_best_survreg(): Get Best Model from Comparison
compare_multiple_survreg(): Compare Multiple Survival Regression Models
print(<multi_survreg_comparison>): Print method for survreg_comparison objects

Internal Utilities

Lower-level helpers. Most users will not call these directly.

filter_call_args(): Filter and merge arguments for function calls
get_combinations_info(): Get all combinations of subgroup factors up to maxk
get_conf_force(): Get forced cut expressions for variables
get_covs_in(): Get indicator vector for selected subgroup factors
process_conf_force_expr(): Process forced cut expression for a variable