# EDI: Experimental Design and Inference [![CRAN](https://img.shields.io/cran/v/EDI.svg)](https://CRAN.R-project.org/package=EDI) [![R-universe version](https://kapelner.r-universe.dev/EDI/badges/version)](https://kapelner.r-universe.dev/EDI) [![R-CMD-check](https://github.com/kapelner/EDI/actions/workflows/R-CMD-check.yaml/badge.svg)](https://github.com/kapelner/EDI/actions/workflows/R-CMD-check.yaml) [![R coverage](https://codecov.io/gh/kapelner/EDI/branch/main/graph/badge.svg?flag=r)](https://app.codecov.io/gh/kapelner/EDI/flags/r) [![License: GPL v3](https://img.shields.io/badge/License-GPLv3-blue.svg)](https://www.gnu.org/licenses/gpl-3.0) [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.22170036.svg)](https://doi.org/10.5281/zenodo.22170036) `EDI` (Experimental Design and Inference) marries experimental designs (fixed and sequential) with inference procedures (exact, asymptotic, and distribution-free) tailored to each design and response type: continuous, incidence, count, proportion, survival with left/right censoring, and ordinal. Designs, inference, and Monte Carlo simulation are exposed as R6 classes; the core estimation and variance-computing kernels are written in C++ (Eigen + LBFGS++) for speed. EDI is not related to Electronic Data Interchange (the business-document exchange standard) or to equity, diversity, and inclusion; it is a statistics package for the design and analysis of randomized experiments. ## Installation Requires R \>= 3.5.0. The quickest route is prebuilt binaries (Linux, macOS, and Windows, no compiler toolchain needed) from Adam Kapelner’s [R-universe](https://kapelner.r-universe.dev): ``` r install.packages( "EDI", repos = c( kapelner = "https://kapelner.r-universe.dev", CRAN = "https://cloud.r-project.org" ) ) ``` > **Not on CRAN yet.** A plain `install.packages("EDI")` fails today — > that does not mean the package doesn’t exist; use the R-universe call > above. `EDI` has been submitted to CRAN and plain > `install.packages("EDI")` will work once accepted. Or install the development version straight from GitHub without cloning (requires a C++ compiler toolchain for R packages, e.g. Rtools on Windows, Xcode command line tools on macOS, or `r-base-dev` on Debian/Ubuntu — this package lives in the `R/EDI` subdirectory of the repository): ``` r remotes::install_github("kapelner/EDI", subdir = "R/EDI") ``` Or from a local clone: ``` r # from the repository root install.packages("R/EDI", repos = NULL, type = "source") ``` ## Getting started ``` r library(EDI) vignette("reproducibility", package = "EDI") # RNG/seed conventions across designs, bootstrap, and simulation vignette("extending-edi", package = "EDI") # writing your own Design/Inference R6 subclasses vignette("backend-contracts", package = "EDI") # how the C++ core is shared between the R (Rcpp) and Python (pybind11) bindings vignette("notation-glossary", package = "EDI") # symbols/naming conventions shared across Design*/Inference* classes and docs vignette("validation-evidence", package = "EDI") # index into the test suite showing each model family computes what it claims ``` See the [repository README](https://github.com/kapelner/EDI#readme) for worked examples (fixed and sequential designs, the inference suite, design bakeoffs via `SimulationFramework`), local performance tuning, and the companion Python package `edi_kernels`. # Package index ## Package Overview - [`EDI-package`](https://kapelner.github.io/EDI/reference/EDI.md) [`EDI`](https://kapelner.github.io/EDI/reference/EDI.md) : Experimental Design and Inference ## Experimental Designs: Fixed-Sample Designs where the sample size n is fixed at construction and treatment assignment is drawn for all n subjects at once, either up front or via assign_w_to_all_subjects() once covariates are recorded. - [`DesignFixed`](https://kapelner.github.io/EDI/reference/DesignFixed.md) : A Fixed Design - [`DesignFixedBernoulli`](https://kapelner.github.io/EDI/reference/DesignFixedBernoulli.md) : A Fixed-Sample-Size Bernoulli (Independent-Coin-Flip) Randomized Design - [`DesignFixediBCRD`](https://kapelner.github.io/EDI/reference/DesignFixediBCRD.md) : A Fixed, Individually Balanced Completely Randomized Design (iBCRD) - [`DesignFixedFactorial`](https://kapelner.github.io/EDI/reference/DesignFixedFactorial.md) : A Fixed, Balanced Two-Arm Factorial Design - [`DesignFixedBlocking`](https://kapelner.github.io/EDI/reference/DesignFixedBlocking.md) : A Fixed, Stratified-Block Randomized Design - [`DesignFixedCluster`](https://kapelner.github.io/EDI/reference/DesignFixedCluster.md) : A Fixed, Unblocked Cluster Randomized Design - [`DesignFixedBlockedCluster`](https://kapelner.github.io/EDI/reference/DesignFixedBlockedCluster.md) : A Fixed, Blocked-and-Clustered Randomized Design - [`DesignFixedBinaryMatch`](https://kapelner.github.io/EDI/reference/DesignFixedBinaryMatch.md) : A Fixed, Non-Bipartite-Matched-Pair Design with Within-Pair Randomization - [`DesignFixedMatchingGreedyPairSwitching`](https://kapelner.github.io/EDI/reference/DesignFixedMatchingGreedyPairSwitching.md) : A Fixed, Matched-Pair Design with Greedy Which-Member-Treated Optimization - [`DesignFixedGreedy`](https://kapelner.github.io/EDI/reference/DesignFixedGreedy.md) : A Fixed, Covariate-Balanced Design via Greedy Pairwise-Swap Search - [`DesignFixedGreedyDOptimal`](https://kapelner.github.io/EDI/reference/DesignFixedGreedyDOptimal.md) : A Fixed, Model-Based Optimal Design via Greedy Pairwise-Exchange Search - [`DesignFixedOptimal`](https://kapelner.github.io/EDI/reference/DesignFixedOptimal.md) : A Fixed, Deterministic Single-Allocation Optimal Design - [`DesignFixedOptimalBlocks`](https://kapelner.github.io/EDI/reference/DesignFixedOptimalBlocks.md) : A Fixed, Covariate-Homogeneous-Block Randomized Design - [`DesignFixedRerandomization`](https://kapelner.github.io/EDI/reference/DesignFixedRerandomization.md) : A Fixed Rerandomization Design (Rejection-Sampled on Covariate Balance) ## Experimental Designs: Sequential (One-by-One) Designs where subjects arrive one at a time and treatment is assigned on arrival via add_one_subject_to_experiment_and_assign(), before the next subject’s covariates are known. This includes the KK “matching-on-the-fly” family, which builds matched pairs from the accruing subject stream. - [`DesignSeqOneByOne`](https://kapelner.github.io/EDI/reference/DesignSeqOneByOne.md) : Sequential One-by-One Experimental Design - [`DesignSeqOneByOneBernoulli`](https://kapelner.github.io/EDI/reference/DesignSeqOneByOneBernoulli.md) : A Sequential Bernoulli (Independent-Coin-Flip) Randomized Design - [`DesignSeqOneByOneiBCRD`](https://kapelner.github.io/EDI/reference/DesignSeqOneByOneiBCRD.md) : A Sequential Design Guaranteeing Exact Terminal Balance (Random Allocation Rule) - [`DesignSeqOneByOneUrn`](https://kapelner.github.io/EDI/reference/DesignSeqOneByOneUrn.md) : Wei's (1977, 1978) Adaptive Urn Sequential Design, UD(\\\alpha\\, \\\beta\\) - [`DesignSeqOneByOneEfron`](https://kapelner.github.io/EDI/reference/DesignSeqOneByOneEfron.md) : Efron's (1971) Biased Coin Sequential Design - [`DesignSeqOneByOneAtkinson`](https://kapelner.github.io/EDI/reference/DesignSeqOneByOneAtkinson.md) : Atkinson's (1982) Covariate-Adjusted Biased Coin Sequential Design - [`DesignSeqOneByOnePocockSimon`](https://kapelner.github.io/EDI/reference/DesignSeqOneByOnePocockSimon.md) : Pocock and Simon's (1975) Minimization Sequential Design - [`DesignSeqOneByOneRandomBlockSize`](https://kapelner.github.io/EDI/reference/DesignSeqOneByOneRandomBlockSize.md) : A Sequential Permuted-Block Design with Randomly Varying Block Sizes - [`DesignSeqOneByOneSPBR`](https://kapelner.github.io/EDI/reference/DesignSeqOneByOneSPBR.md) : A Stratified Permuted-Block Sequential Design (SPBR) with Fixed Block Size - [`DesignSeqOneByOneKK14`](https://kapelner.github.io/EDI/reference/DesignSeqOneByOneKK14.md) : Kapelner and Krieger's (2014) Sequential "Matching-on-the-Fly" Design - [`DesignSeqOneByOneKK21`](https://kapelner.github.io/EDI/reference/DesignSeqOneByOneKK21.md) : Kapelner and Krieger's (2021) Outcome-Weighted Sequential Matching-on-the-Fly Design - [`DesignSeqOneByOneKK21stepwise`](https://kapelner.github.io/EDI/reference/DesignSeqOneByOneKK21stepwise.md) : Stepwise Variant of the KK21 Outcome-Weighted Sequential Matching Design ## Experimental Designs: Observational Designs for already-observed (non-randomized) treatment assignments – the design object acts as a data container with matched-pair/blocking structure, but does not itself draw any randomization. - [`ObservationalDesign`](https://kapelner.github.io/EDI/reference/ObservationalDesign.md) : A Fixed Observational (Non-Randomized) Design - [`ObservationalDesignBlocks`](https://kapelner.github.io/EDI/reference/ObservationalDesignBlocks.md) : A Fixed Observational (Non-Randomized) Design With Blocks - [`ObservationalDesignMatching`](https://kapelner.github.io/EDI/reference/ObservationalDesignMatching.md) : A Fixed Observational (Non-Randomized) Matched-Pair Design ## Design: Custom Extensions Base classes for plugging in a user-defined assignment/drawing rule. - [`DesignFixedCustom`](https://kapelner.github.io/EDI/reference/DesignFixedCustom.md) : Internal base for user-defined fixed-design extensions - [`DesignCustomSequential`](https://kapelner.github.io/EDI/reference/DesignCustomSequential.md) : Internal base for user-defined sequential-design extensions ## Design: Infrastructure Abstract bases, capability components, and shared machinery – not typically constructed directly. See vignette(“backend-contracts”) and fix_design_hierarchy.md for the capability/component model these implement. - [`Design`](https://kapelner.github.io/EDI/reference/Design.md) : An Abstract Experimental Design ## Inference: Continuous Outcomes - [`InferenceContinKKGLMM`](https://kapelner.github.io/EDI/reference/InferenceContinKKGLMM.md) : Linear Mixed Model Inference for KK Designs with Continuous Response - [`InferenceContinKKOLSIVWC`](https://kapelner.github.io/EDI/reference/InferenceContinKKOLSIVWC.md) : OLS IVWC Compound Inference for KK Designs - [`InferenceContinKKOLSOneLik`](https://kapelner.github.io/EDI/reference/InferenceContinKKOLSOneLik.md) : OLS Combined-Likelihood Inference for KK Designs - [`InferenceContinKKQuantileRegrIVWC`](https://kapelner.github.io/EDI/reference/InferenceContinKKQuantileRegrIVWC.md) : Quantile Regression Compound Estimator for KK Matching-on-the-Fly Designs - [`InferenceContinKKQuantileRegrOneLik`](https://kapelner.github.io/EDI/reference/InferenceContinKKQuantileRegrOneLik.md) : Quantile Regression Combined-Likelihood Compound Estimator for KK Designs (Continuous) - [`InferenceContinKKRobustRegrIVWC`](https://kapelner.github.io/EDI/reference/InferenceContinKKRobustRegrIVWC.md) : Robust-Regression IVWC Compound Inference for KK Designs - [`InferenceContinKKRobustRegrOneLik`](https://kapelner.github.io/EDI/reference/InferenceContinKKRobustRegrOneLik.md) : Robust-Regression Combined-Likelihood Inference for KK Designs - [`InferenceContinLin`](https://kapelner.github.io/EDI/reference/InferenceContinLin.md) : Lin (2013) Covariate-Adjusted OLS Inference for Continuous Responses - [`InferenceContinOLS`](https://kapelner.github.io/EDI/reference/InferenceContinOLS.md) : OLS Inference for Continuous Responses - [`InferenceContinQuantileRegr`](https://kapelner.github.io/EDI/reference/InferenceContinQuantileRegr.md) : Quantile Regression Inference for Continuous Responses - [`InferenceContinRobustRegr`](https://kapelner.github.io/EDI/reference/InferenceContinRobustRegr.md) : Robust (M/MM-Estimator) Regression Inference for Continuous Responses - [`InferenceBaiAdjustedTKK14`](https://kapelner.github.io/EDI/reference/InferenceBaiAdjustedTKK14.md) : Bai Adjusted-t Mean-Difference Inference for KK14 Designs - [`InferenceBaiAdjustedTKK21`](https://kapelner.github.io/EDI/reference/InferenceBaiAdjustedTKK21.md) : Bai Adjusted-t Mean-Difference Inference for KK21 Designs ## Inference: Incidence (Binary) Outcomes - [`InferenceIncidBinomialIdentityRiskDiff`](https://kapelner.github.io/EDI/reference/InferenceIncidBinomialIdentityRiskDiff.md) : Binomial Identity Risk Difference Inference for Incidence Responses - [`InferenceIncidCMH`](https://kapelner.github.io/EDI/reference/InferenceIncidCMH.md) : CMH Blocked Incidence Inference - [`InferenceIncidExactBinomial`](https://kapelner.github.io/EDI/reference/InferenceIncidExactBinomial.md) : Exact Binomial (McNemar-Type) Incidence Inference for Matched-Pair Designs - [`InferenceIncidExactFisher`](https://kapelner.github.io/EDI/reference/InferenceIncidExactFisher.md) : Exact Fisher (Conditional Hypergeometric) Incidence Inference - [`InferenceIncidExactZhang`](https://kapelner.github.io/EDI/reference/InferenceIncidExactZhang.md) : Exact Zhang Combined-Test Incidence Inference - [`InferenceIncidExtendedRobins`](https://kapelner.github.io/EDI/reference/InferenceIncidExtendedRobins.md) : Extended Robins Blocked Incidence Inference - [`InferenceIncidGCompRiskDiff`](https://kapelner.github.io/EDI/reference/InferenceIncidGCompRiskDiff.md) : G-Computation Risk-Difference Inference for Binary Responses - [`InferenceIncidGCompRiskRatio`](https://kapelner.github.io/EDI/reference/InferenceIncidGCompRiskRatio.md) : G-Computation Risk-Ratio Inference for Binary Responses - [`InferenceIncidKKCondLogitGLMMIVWC`](https://kapelner.github.io/EDI/reference/InferenceIncidKKCondLogitGLMMIVWC.md) : Conditional Logistic Plus GLMM IVWC Inference for KK Designs - [`InferenceIncidKKCondLogitGLMMOneLik`](https://kapelner.github.io/EDI/reference/InferenceIncidKKCondLogitGLMMOneLik.md) : Conditional Logistic Plus GLMM Combined-Likelihood Inference for KK Designs - [`InferenceIncidKKCondLogitIVWC`](https://kapelner.github.io/EDI/reference/InferenceIncidKKCondLogitIVWC.md) : Conditional Logistic IVWC Inference (KK Designs, Binary Response) - [`InferenceIncidKKCondLogitOneLik`](https://kapelner.github.io/EDI/reference/InferenceIncidKKCondLogitOneLik.md) : One-Likelihood Conditional-Logistic Inference for KK Binary Designs - [`InferenceIncidKKGCompRiskDiff`](https://kapelner.github.io/EDI/reference/InferenceIncidKKGCompRiskDiff.md) : G-Computation Risk-Difference Inference for KK Designs with Binary Responses - [`InferenceIncidKKGCompRiskRatio`](https://kapelner.github.io/EDI/reference/InferenceIncidKKGCompRiskRatio.md) : G-Computation Risk-Ratio Inference for KK Designs with Binary Responses - [`InferenceIncidKKGEE`](https://kapelner.github.io/EDI/reference/InferenceIncidKKGEE.md) : GEE Inference for KK Designs with Binary Response - [`InferenceIncidKKModifiedPoisson`](https://kapelner.github.io/EDI/reference/InferenceIncidKKModifiedPoisson.md) : Modified-Poisson Inference for KK Designs with Binary Responses - [`KKNewcombeRiskDiffIVWCSource`](https://kapelner.github.io/EDI/reference/InferenceIncidKKNewcombeRiskDiff.md) : KK Newcombe Risk-Difference IVWC Inference for Binary Responses - [`InferenceIncidLogBinomial`](https://kapelner.github.io/EDI/reference/InferenceIncidLogBinomial.md) : Log-Binomial Regression Inference for Incidence Responses - [`InferenceIncidLogRegr`](https://kapelner.github.io/EDI/reference/InferenceIncidLogRegr.md) : Logistic Regression Inference for Incidence Responses - [`InferenceIncidMiettinenNurminenRiskDiff`](https://kapelner.github.io/EDI/reference/InferenceIncidMiettinenNurminenRiskDiff.md) : Miettinen-Nurminen Risk-Difference Inference for Binary Responses - [`InferenceIncidModifiedPoisson`](https://kapelner.github.io/EDI/reference/InferenceIncidModifiedPoisson.md) : Modified Poisson Regression Inference for Incidence Responses - [`InferenceIncidNewcombeRiskDiff`](https://kapelner.github.io/EDI/reference/InferenceIncidNewcombeRiskDiff.md) : Newcombe Risk-Difference Inference for Binary Responses - [`InferenceIncidProbitRegr`](https://kapelner.github.io/EDI/reference/InferenceIncidProbitRegr.md) : Probit Regression Inference for Incidence Responses - [`InferenceIncidRiskDiff`](https://kapelner.github.io/EDI/reference/InferenceIncidRiskDiff.md) : Risk Difference Inference for Incidence Responses - [`InferenceIncidWald`](https://kapelner.github.io/EDI/reference/InferenceIncidWald.md) : Wald Incidence Inference ## Inference: Count Outcomes - [`InferenceCountHurdleNegBin`](https://kapelner.github.io/EDI/reference/InferenceCountHurdleNegBin.md) : Hurdle Negative Binomial Regression Inference for Count Responses - [`InferenceCountHurdlePoisson`](https://kapelner.github.io/EDI/reference/InferenceCountHurdlePoisson.md) : Hurdle Poisson Regression Inference for Count Responses - [`InferenceCountKKCondPoissonOneLik`](https://kapelner.github.io/EDI/reference/InferenceCountKKCondPoissonOneLik.md) : One-Likelihood Conditional-Poisson Inference for KK Count Designs - [`InferenceCountKKGLMM`](https://kapelner.github.io/EDI/reference/InferenceCountKKGLMM.md) : GLMM Inference for KK Designs with Count Response - [`InferenceCountKKHurdlePoissonIVWC`](https://kapelner.github.io/EDI/reference/InferenceCountKKHurdlePoissonIVWC.md) : KK Hurdle Poisson IVWC Inference for Count Responses - [`InferenceCountKKHurdlePoissonOneLik`](https://kapelner.github.io/EDI/reference/InferenceCountKKHurdlePoissonOneLik.md) : KK Hurdle-Poisson Combined-Likelihood Inference for Count Responses - [`InferenceCountNegBin`](https://kapelner.github.io/EDI/reference/InferenceCountNegBin.md) : Negative Binomial Regression Inference for Count Responses - [`InferenceCountPoisson`](https://kapelner.github.io/EDI/reference/InferenceCountPoisson.md) : Poisson Regression Inference for Count Responses - [`InferenceCountPoissonKKGEE`](https://kapelner.github.io/EDI/reference/InferenceCountPoissonKKGEE.md) : GEE Inference for KK Designs with Count Response - [`InferenceCountQuasiPoisson`](https://kapelner.github.io/EDI/reference/InferenceCountQuasiPoisson.md) : Quasi-Poisson Regression Inference for Count Responses - [`InferenceCountRobustPoisson`](https://kapelner.github.io/EDI/reference/InferenceCountRobustPoisson.md) : Robust (Sandwich-Variance) Poisson Regression Inference for Count Responses - [`InferenceCountZeroInflatedNegBin`](https://kapelner.github.io/EDI/reference/InferenceCountZeroInflatedNegBin.md) : Zero-Inflated Negative Binomial Regression Inference for Count Responses - [`InferenceCountZeroInflatedPoisson`](https://kapelner.github.io/EDI/reference/InferenceCountZeroInflatedPoisson.md) : Zero-Inflated Poisson Regression Inference for Count Responses ## Inference: Proportion Outcomes - [`InferencePropBetaRegr`](https://kapelner.github.io/EDI/reference/InferencePropBetaRegr.md) : Beta Regression Inference for Proportion Responses - [`InferencePropFractionalLogit`](https://kapelner.github.io/EDI/reference/InferencePropFractionalLogit.md) : Fractional Logit Inference for Proportion Responses - [`InferencePropGCompMeanDiff`](https://kapelner.github.io/EDI/reference/InferencePropGCompMeanDiff.md) : G-Computation Mean-Difference Inference for Proportion Responses - [`InferencePropKKGEE`](https://kapelner.github.io/EDI/reference/InferencePropKKGEE.md) : GEE Inference for KK Designs with Proportion Response - [`InferencePropKKGLMM`](https://kapelner.github.io/EDI/reference/InferencePropKKGLMM.md) : KK GLMM Inference for Proportion Responses - [`InferencePropKKQuantileRegrIVWC`](https://kapelner.github.io/EDI/reference/InferencePropKKQuantileRegrIVWC.md) : Quantile Regression Compound Estimator for KK Matching-on-the-Fly Designs (Proportion Outcomes) - [`InferencePropKKQuantileRegrOneLik`](https://kapelner.github.io/EDI/reference/InferencePropKKQuantileRegrOneLik.md) : Quantile Regression Combined-Likelihood Compound Estimator for KK Designs (Proportion) - [`InferencePropQuantileRegr`](https://kapelner.github.io/EDI/reference/InferencePropQuantileRegr.md) : Quantile Regression Inference for Proportion Responses - [`InferencePropZeroOneInflatedBetaRegr`](https://kapelner.github.io/EDI/reference/InferencePropZeroOneInflatedBetaRegr.md) : Zero/One-Inflated Beta Inference for Proportion Responses ## Inference: Ordinal Outcomes - [`InferenceOrdinalAdjCatLogitRegr`](https://kapelner.github.io/EDI/reference/InferenceOrdinalAdjCatLogitRegr.md) : Adjacent Category Logit Regression Inference for Ordinal Responses - [`InferenceOrdinalCauchitRegr`](https://kapelner.github.io/EDI/reference/InferenceOrdinalCauchitRegr.md) : Cauchit Regression Inference for Ordinal Responses - [`InferenceOrdinalCloglogRegr`](https://kapelner.github.io/EDI/reference/InferenceOrdinalCloglogRegr.md) : Cumulative Cloglog Inference for Ordinal Responses - [`InferenceOrdinalContRatioRegr`](https://kapelner.github.io/EDI/reference/InferenceOrdinalContRatioRegr.md) : Continuation Ratio Regression Inference for Ordinal Responses - [`InferenceOrdinalGCompMeanDiff`](https://kapelner.github.io/EDI/reference/InferenceOrdinalGCompMeanDiff.md) : G-Computation Mean-Difference Inference for Ordinal Responses - [`InferenceOrdinalJonckheereTerpstraTest`](https://kapelner.github.io/EDI/reference/InferenceOrdinalJonckheereTerpstraTest.md) : Jonckheere-Terpstra (JT) Test for Ordinal Responses - [`InferenceOrdinalKKCLMM`](https://kapelner.github.io/EDI/reference/InferenceOrdinalKKCLMM.md) : Ordinal KK CLMM (Proportional Odds / logit link) - [`InferenceOrdinalKKCLMMCauchit`](https://kapelner.github.io/EDI/reference/InferenceOrdinalKKCLMMCauchit.md) : Ordinal KK CLMM (Cauchit link) - [`InferenceOrdinalKKCLMMCloglog`](https://kapelner.github.io/EDI/reference/InferenceOrdinalKKCLMMCloglog.md) : Ordinal KK CLMM (Complementary log-log link) - [`InferenceOrdinalKKCLMMProbit`](https://kapelner.github.io/EDI/reference/InferenceOrdinalKKCLMMProbit.md) : Ordinal KK CLMM (Probit link) - [`InferenceOrdinalKKCondAdjCatLogitRegr`](https://kapelner.github.io/EDI/reference/InferenceOrdinalKKCondAdjCatLogitRegr.md) : Adjacent Category Logit Inference for KK Matching-on-the-fly Designs - [`InferenceOrdinalKKGEE`](https://kapelner.github.io/EDI/reference/InferenceOrdinalKKGEE.md) : GEE Inference for KK Designs with Ordinal Response - [`InferenceOrdinalKKGLMM`](https://kapelner.github.io/EDI/reference/InferenceOrdinalKKGLMM.md) : GLMM Inference for KK Designs with Ordinal Response - [`InferenceOrdinalOrderedProbitRegr`](https://kapelner.github.io/EDI/reference/InferenceOrdinalOrderedProbitRegr.md) : Ordered Probit Regression Inference for Ordinal Responses - [`InferenceOrdinalPairedSignTest`](https://kapelner.github.io/EDI/reference/InferenceOrdinalPairedSignTest.md) : Paired Sign Test Inference for KK Designs with Ordinal Response - [`InferenceOrdinalPartialProportionalOddsRegr`](https://kapelner.github.io/EDI/reference/InferenceOrdinalPartialProportionalOddsRegr.md) : Partial Proportional-Odds Regression Inference for Ordinal Responses - [`InferenceOrdinalPropOddsRegr`](https://kapelner.github.io/EDI/reference/InferenceOrdinalPropOddsRegr.md) : Proportional Odds Regression Inference for Ordinal Responses - [`InferenceOrdinalRidit`](https://kapelner.github.io/EDI/reference/InferenceOrdinalRidit.md) : Ridit Analysis for Ordinal Responses - [`InferenceOrdinalStereotypeLogitRegr`](https://kapelner.github.io/EDI/reference/InferenceOrdinalStereotypeLogitRegr.md) : Stereotype Logit Regression Inference for Ordinal Responses ## Inference: Survival Outcomes - [`InferenceSurvivalCoxPHRegr`](https://kapelner.github.io/EDI/reference/InferenceSurvivalCoxPHRegr.md) : Cox Proportional Hazards Regression Inference for Survival Responses - [`InferenceSurvivalDepCensTransformRegr`](https://kapelner.github.io/EDI/reference/InferenceSurvivalDepCensTransformRegr.md) : Dependent-Censoring Transformation Inference for Survival Responses - [`InferenceSurvivalGLMMWeibullFrailtyLoggammaIVWC`](https://kapelner.github.io/EDI/reference/InferenceSurvivalGLMMWeibullFrailtyLoggammaIVWC.md) : Clayton Copula / Standard Weibull Compound Inference for KK Designs - [`InferenceSurvivalGLMMWeibullFrailtyLoggammaOneLik`](https://kapelner.github.io/EDI/reference/InferenceSurvivalGLMMWeibullFrailtyLoggammaOneLik.md) : One-Likelihood Clayton-Copula Weibull AFT Inference for KK Survival Designs - [`InferenceSurvivalGLMMWeibullFrailtyNormalIVWC`](https://kapelner.github.io/EDI/reference/InferenceSurvivalGLMMWeibullFrailtyNormalIVWC.md) : Weibull Frailty IVWC Inference for KK Designs - [`InferenceSurvivalGLMMWeibullFrailtyNormalOneLik`](https://kapelner.github.io/EDI/reference/InferenceSurvivalGLMMWeibullFrailtyNormalOneLik.md) : Weibull Frailty Combined-Likelihood Inference for KK Designs - [`InferenceSurvivalGehanWilcox`](https://kapelner.github.io/EDI/reference/InferenceSurvivalGehanWilcox.md) : Gehan-Wilcoxon (Peto-Prentice) Inference for Survival Data with Censoring - [`InferenceSurvivalKKLWACoxPHIVWC`](https://kapelner.github.io/EDI/reference/InferenceSurvivalKKLWACoxPHIVWC.md) : LWA-style Marginal Cox IVWC Compound Inference for KK Designs - [`InferenceSurvivalKKLWACoxPHOneLik`](https://kapelner.github.io/EDI/reference/InferenceSurvivalKKLWACoxPHOneLik.md) : LWA-style Marginal Cox Combined-Likelihood Inference for KK Designs - [`InferenceSurvivalKKRankRegrIVWC`](https://kapelner.github.io/EDI/reference/InferenceSurvivalKKRankRegrIVWC.md) : Rank Regression Inference for Survival Responses under KK Designs - [`InferenceSurvivalKKStratCoxPHIVWC`](https://kapelner.github.io/EDI/reference/InferenceSurvivalKKStratCoxPHIVWC.md) : Stratified Cox / Standard Cox Compound Inference for KK Designs - [`InferenceSurvivalKKStratCoxPHOneLik`](https://kapelner.github.io/EDI/reference/InferenceSurvivalKKStratCoxPHOneLik.md) : Stratified Cox Combined-Likelihood Compound Inference for KK Designs - [`SurvivalKKWeibullMarginalSource`](https://kapelner.github.io/EDI/reference/InferenceSurvivalKKWeibullMarginal.md) : Marginal (Cluster-Robust) Weibull Inference for KK Matched-Pair Survival Designs - [`InferenceSurvivalKMDiff`](https://kapelner.github.io/EDI/reference/InferenceSurvivalKMDiff.md) : Kaplan-Meier Median-Difference Inference for Survival Responses - [`InferenceSurvivalLogRank`](https://kapelner.github.io/EDI/reference/InferenceSurvivalLogRank.md) : Log-Rank Inference for Survival Data with Censoring - [`InferenceSurvivalRestrictedMeanDiff`](https://kapelner.github.io/EDI/reference/InferenceSurvivalRestrictedMeanDiff.md) : Restricted Mean Survival Time (RMST) Difference Inference for Survival Responses - [`InferenceSurvivalStratCoxPHRegr`](https://kapelner.github.io/EDI/reference/InferenceSurvivalStratCoxPHRegr.md) : Stratified Cox PH Inference for Survival Responses - [`InferenceSurvivalWeibullRegr`](https://kapelner.github.io/EDI/reference/InferenceSurvivalWeibullRegr.md) : Weibull AFT Inference for Survival Responses ## Inference: Cross-Cutting / General Estimators and coordinators that work across more than one response type, rather than being tied to a single outcome family. - [`InferenceAllKKMeanDiffIVWC`](https://kapelner.github.io/EDI/reference/InferenceAllKKMeanDiffIVWC.md) : Mean-Difference IVWC Inference for KK Matching-on-the-Fly Designs - [`InferenceAllKKWilcoxIVWC`](https://kapelner.github.io/EDI/reference/InferenceAllKKWilcoxIVWC.md) : Non-parametric Wilcoxon-based Compound Inference for KK Matching-on-the-Fly Designs - [`InferenceAllSimpleAverageDiff`](https://kapelner.github.io/EDI/reference/InferenceAllSimpleAverageDiff.md) : Simple Mean-Difference Inference for Continuous Responses - [`InferenceAllSimpleMeanDiffPooledVar`](https://kapelner.github.io/EDI/reference/InferenceAllSimpleMeanDiffPooledVar.md) : Simple Mean-Difference Inference with Pooled Variance - [`InferenceAllSimpleWilcox`](https://kapelner.github.io/EDI/reference/InferenceAllSimpleWilcox.md) : Simple Wilcoxon Rank-Sum (Hodges-Lehmann) Inference - [`InferenceSuite`](https://kapelner.github.io/EDI/reference/InferenceSuite.md) : Inference Suite: Discover and Bundle Every Applicable Inference Class for a Design - [`print(`*``*`)`](https://kapelner.github.io/EDI/reference/print.EDIInferenceSuiteResults.md) : Prints the results table from an [`InferenceSuite`](https://kapelner.github.io/EDI/reference/InferenceSuite.html) `run_all_inference()` call – the same table `screen = TRUE` prints during the call itself, so a user who assigned the return value and later types its name (or calls [`print()`](https://rdrr.io/r/base/print.html) on it) sees a readable table rather than a raw nested list dump. The table itself is rendered by `run_all_inference_format_pretty_table()`: rows sorted by `estimand`, with a double rule under the header and a single rule between `estimand` groups and at the bottom, class names and `estimand` values shortened for display (never the underlying `results_table` values), and a `cov_model` letter-key legend appended when applicable – see that function's own documentation for the exact column-by-column rendering rules. - [`summary(`*``*`)`](https://kapelner.github.io/EDI/reference/summary.EDIInferenceSuiteResults.md) [`print(`*``*`)`](https://kapelner.github.io/EDI/reference/summary.EDIInferenceSuiteResults.md) : Summarizes an [`InferenceSuite`](https://kapelner.github.io/EDI/reference/InferenceSuite.html) `run_all_inference()` result: counts by `status`, the estimate range across `status == "ok"` classes, and how many reject at `alpha`. - [`EDI_COMPREHENSIVE_SLOW_PATHS`](https://kapelner.github.io/EDI/reference/EDI_COMPREHENSIVE_SLOW_PATHS.md) : Comprehensive-test slow-path registry ## Inference: Custom Extensions Base classes for plugging in a user-defined asymptotic/bootstrap/randomization estimator. - [`InferenceCustomAsymp`](https://kapelner.github.io/EDI/reference/InferenceCustomAsymp.md) : Internal base for user-defined asymptotic inference extensions - [`InferenceCustomBoot`](https://kapelner.github.io/EDI/reference/InferenceCustomBoot.md) : Internal base for user-defined bootstrap inference extensions - [`InferenceCustomRand`](https://kapelner.github.io/EDI/reference/InferenceCustomRand.md) : Internal base for user-defined randomization inference extensions - [`InferenceRandCustom`](https://kapelner.github.io/EDI/reference/InferenceRandCustom.md) : Randomization test/CI on a user-supplied statistic ## Inference: Infrastructure Abstract bases, resampling/likelihood mixins, and matched-design (KK) family bases – not typically constructed directly. See vignette(“reproducibility”) for the resampling mixins’ RNG/seed conventions and vignette(“notation-glossary”) for shared symbols. - [`Inference`](https://kapelner.github.io/EDI/reference/Inference.md) : Inference for A Sequential Design - [`InferenceAsymp`](https://kapelner.github.io/EDI/reference/InferenceAsymp.md) : Asymptotic Inference - [`InferenceAsympLik`](https://kapelner.github.io/EDI/reference/InferenceAsympLik.md) : Likelihood-Backed Asymptotic Inference - [`InferenceRand`](https://kapelner.github.io/EDI/reference/InferenceRand.md) : Randomization-based Inference - [`InferenceRandBootstrap`](https://kapelner.github.io/EDI/reference/InferenceRandBootstrap.md) : Bootstrap Randomization Test Inference - [`InferenceRandBootstrapCI`](https://kapelner.github.io/EDI/reference/InferenceRandBootstrapCI.md) : Bootstrap Randomization Confidence Intervals - [`InferenceNonParamBootstrap`](https://kapelner.github.io/EDI/reference/InferenceNonParamBootstrap.md) : Bootstrap-based Inference - [`InferenceParamBootstrap`](https://kapelner.github.io/EDI/reference/InferenceParamBootstrap.md) : Parametric-Bootstrap-Capable Likelihood Inference - [`InferenceBayesianBootstrap`](https://kapelner.github.io/EDI/reference/InferenceBayesianBootstrap.md) : Bayesian Bootstrap-capable Inference - [`InferenceJackknife`](https://kapelner.github.io/EDI/reference/InferenceJackknife.md) : Jackknife-based Inference - [`CountLikelihoodPlumbingSource`](https://kapelner.github.io/EDI/reference/InferenceCountLikelihood.md) : Count-Specific Likelihood Inference - [`kk_passthrough_compound_host_public`](https://kapelner.github.io/EDI/reference/InferenceKKPassThroughCompound.md) : Internal Base Class for KK Matching-on-the-Fly Designs - [`InferenceMLEorKMSummaryTable`](https://kapelner.github.io/EDI/reference/InferenceMLEorKMSummaryTable.md) : Inference for A Sequential Design - [`InferenceAbstractQuantileRandCI`](https://kapelner.github.io/EDI/reference/InferenceAbstractQuantileRandCI.md) : Abstract mixin: Zhang combined randomisation CI for quantile regression - [`InferenceAbstractKKCondLogitGLMM`](https://kapelner.github.io/EDI/reference/InferenceAbstractKKCondLogitGLMM.md) : Abstract Conditional Logistic GLMM Inference - [`InferenceAbstractKKMarginalIncid`](https://kapelner.github.io/EDI/reference/InferenceAbstractKKMarginalIncid.md) : Abstract class for all-subject marginal incidence inference in KK designs - [`InferenceAbstractKKModifiedPoisson`](https://kapelner.github.io/EDI/reference/InferenceAbstractKKModifiedPoisson.md) : Abstract class for all-subject modified-Poisson inference in KK designs - [`InferenceAbstractKKOrdinalCLMM`](https://kapelner.github.io/EDI/reference/InferenceAbstractKKOrdinalCLMM.md) : Abstract class for ordinal CLMM-based Inference in KK designs ## Simulation Framework Monte Carlo simulation for comparing designs and inference methods, and for computing the coverage_pval/size_pval calibration diagnostics documented in vignette(“validation-evidence”). - [`SimulationFramework`](https://kapelner.github.io/EDI/reference/SimulationFramework.md) : Simulation Framework for Experimental Designs and Inference Methods - [`SimulationFrameworkReport`](https://kapelner.github.io/EDI/reference/SimulationFrameworkReport.md) : Reporting class for SimulationFramework results - [`generate_covariate_dataset()`](https://kapelner.github.io/EDI/reference/generate_covariate_dataset.md) : Generate Synthetic Simulation Covariates and Continuous Response - [`transform_cont_y_based_on_response_type()`](https://kapelner.github.io/EDI/reference/transform_cont_y_based_on_response_type.md) : Transform continuous latent signal to the response type scale ## Backend: Continuous & Robust Regression Kernels See vignette(“backend-contracts”) for the shared conventions these C++ kernels follow. - [`fast_ols_cpp()`](https://kapelner.github.io/EDI/reference/fast_ols_cpp.md) : Fast Ordinary Least Squares (OLS) Regression, Estimate-Only (C++ Backend) - [`fast_ols_with_var_cpp()`](https://kapelner.github.io/EDI/reference/fast_ols_with_var_cpp.md) : Fast Ordinary Least Squares (OLS) Regression with Variance (C++ Backend) - [`ols_hc2_post_fit_cpp()`](https://kapelner.github.io/EDI/reference/ols_hc2_post_fit_cpp.md) : Export of C++ function ols_hc2_post_fit_cpp ## Backend: Binary/Incidence Regression Kernels - [`fast_logistic_regression()`](https://kapelner.github.io/EDI/reference/fast_logistic_regression.md) : Fast Logistic Regression, Estimate Only (R Wrapper) - [`fast_logistic_regression_cpp()`](https://kapelner.github.io/EDI/reference/fast_logistic_regression_cpp.md) : Fast Logistic Regression, Estimate Only (C++ Backend) - [`fast_logistic_regression_weighted_cpp()`](https://kapelner.github.io/EDI/reference/fast_logistic_regression_weighted_cpp.md) : Fast Weighted Logistic Regression, Estimate Only (C++ Backend) - [`fast_logistic_regression_with_var()`](https://kapelner.github.io/EDI/reference/fast_logistic_regression_with_var.md) : Fast Logistic Regression with Variance, Auto-Retrying on Separation (R Wrapper) - [`fast_logistic_regression_with_var_cpp()`](https://kapelner.github.io/EDI/reference/fast_logistic_regression_with_var_cpp.md) : Fast Logistic Regression with Targeted Variance (C++ Backend) - [`get_identity_binomial_regression_hessian_cpp()`](https://kapelner.github.io/EDI/reference/get_identity_binomial_regression_hessian_cpp.md) : Identity-Link (Risk-Difference) Binomial Regression Hessian, Standalone (C++) - [`get_identity_binomial_regression_score_cpp()`](https://kapelner.github.io/EDI/reference/get_identity_binomial_regression_score_cpp.md) : Identity-Link (Risk-Difference) Binomial Regression Score, Standalone (C++) - [`get_identity_binomial_regression_weighted_hessian_cpp()`](https://kapelner.github.io/EDI/reference/get_identity_binomial_regression_weighted_hessian_cpp.md) : Weighted Identity-Link (Risk-Difference) Binomial Regression Hessian, Standalone (C++) - [`get_identity_binomial_regression_weighted_score_cpp()`](https://kapelner.github.io/EDI/reference/get_identity_binomial_regression_weighted_score_cpp.md) : Weighted Identity-Link (Risk-Difference) Binomial Regression Score, Standalone (C++) - [`get_log_binomial_regression_hessian_cpp()`](https://kapelner.github.io/EDI/reference/get_log_binomial_regression_hessian_cpp.md) : Log-Link (Relative-Risk) Binomial Regression Hessian, Standalone (C++) - [`get_log_binomial_regression_score_cpp()`](https://kapelner.github.io/EDI/reference/get_log_binomial_regression_score_cpp.md) : Log-Link (Relative-Risk) Binomial Regression Score, Standalone (C++) - [`get_log_binomial_regression_weighted_hessian_cpp()`](https://kapelner.github.io/EDI/reference/get_log_binomial_regression_weighted_hessian_cpp.md) : Weighted Log-Link (Relative-Risk) Binomial Regression Hessian, Standalone (C++) - [`get_log_binomial_regression_weighted_score_cpp()`](https://kapelner.github.io/EDI/reference/get_log_binomial_regression_weighted_score_cpp.md) : Weighted Log-Link (Relative-Risk) Binomial Regression Score, Standalone (C++) - [`gcomp_logistic_point_estimate_cpp()`](https://kapelner.github.io/EDI/reference/gcomp_logistic_point_estimate_cpp.md) : Fast G-Computation (Standardization) Point Estimate for Logistic Regression (C++) - [`gcomp_logistic_post_fit_cpp()`](https://kapelner.github.io/EDI/reference/gcomp_logistic_post_fit_cpp.md) : Export of C++ function gcomp_logistic_post_fit_cpp - [`gcomp_fractional_logit_point_estimate_cpp()`](https://kapelner.github.io/EDI/reference/gcomp_fractional_logit_point_estimate_cpp.md) : Fast G-Computation (Standardization) Point Estimate for a Logit-Link Model (C++) - [`mn_pvalue_cpp()`](https://kapelner.github.io/EDI/reference/mn_pvalue_cpp.md) : Export of C++ function mn_pvalue_cpp - [`newcombe_independent_ci_cpp()`](https://kapelner.github.io/EDI/reference/newcombe_independent_ci_cpp.md) : Export of C++ function newcombe_independent_ci_cpp ## Backend: Count Regression Kernels - [`fast_poisson_regression_cpp()`](https://kapelner.github.io/EDI/reference/fast_poisson_regression_cpp.md) : Fast Poisson Regression, Estimate-Only (C++ Backend) - [`fast_poisson_regression_weighted_cpp()`](https://kapelner.github.io/EDI/reference/fast_poisson_regression_weighted_cpp.md) : Fast Weighted Poisson Regression (C++ Backend) - [`fast_poisson_regression_with_var_cpp()`](https://kapelner.github.io/EDI/reference/fast_poisson_regression_with_var_cpp.md) : Fast Poisson Regression with Variance Calculation (C++ Backend) - [`fast_quasipoisson_regression_with_var_cpp()`](https://kapelner.github.io/EDI/reference/fast_quasipoisson_regression_with_var_cpp.md) : Fast Quasi-Poisson Regression with Variance Calculation (C++ Backend) - [`fast_negbin_regression()`](https://kapelner.github.io/EDI/reference/fast_negbin_regression.md) : Fast Negative Binomial Regression, Estimate-Only (R Wrapper) - [`fast_negbin_regression_with_var()`](https://kapelner.github.io/EDI/reference/fast_negbin_regression_with_var.md) : Fast Negative Binomial Regression with Variance Calculation (R Wrapper) - [`fast_cpoisson_combined_with_var_cpp()`](https://kapelner.github.io/EDI/reference/fast_cpoisson_combined_with_var_cpp.md) : Fast Combined Conditional-Poisson + Poisson Regression for KK Matched-Pair/ Reservoir Designs, with Variance (C++ Backend) - [`get_cpoisson_combined_hessian_cpp()`](https://kapelner.github.io/EDI/reference/get_cpoisson_combined_hessian_cpp.md) : Combined Conditional-Poisson/Poisson Hessian, Standalone (C++) - [`get_cpoisson_combined_score_cpp()`](https://kapelner.github.io/EDI/reference/get_cpoisson_combined_score_cpp.md) : Combined Conditional-Poisson/Poisson Score, Standalone (C++) - [`get_negbin_regression_hessian_cpp()`](https://kapelner.github.io/EDI/reference/get_negbin_regression_hessian_cpp.md) : Negative Binomial Regression Hessian, Standalone (C++) - [`get_negbin_regression_score_cpp()`](https://kapelner.github.io/EDI/reference/get_negbin_regression_score_cpp.md) : Compute Negative Binomial Regression Score ## Backend: Ordinal Regression Kernels - [`expand_adjacent_category_data_cpp()`](https://kapelner.github.io/EDI/reference/expand_adjacent_category_data_cpp.md) : Expand Ordinal Data into Stacked Binary Comparisons for Adjacent-Category Logit Regression (C++ Backend) - [`expand_continuation_ratio_data_cpp()`](https://kapelner.github.io/EDI/reference/expand_continuation_ratio_data_cpp.md) : Expand Ordinal Data into Stacked Binary Comparisons for Continuation-Ratio Regression (C++ Backend) - [`exact_jonckheere_terpstra_pval_cpp()`](https://kapelner.github.io/EDI/reference/exact_jonckheere_terpstra_pval_cpp.md) : Exact Two-Group Jonckheere-Terpstra Test via Full Randomization Enumeration (C++ Backend) - [`gcomp_ordinal_proportional_odds_post_fit_cpp()`](https://kapelner.github.io/EDI/reference/gcomp_ordinal_proportional_odds_post_fit_cpp.md) : Export of C++ function gcomp_ordinal_proportional_odds_post_fit_cpp - [`ordinal_gcomp_post_fit_cpp()`](https://kapelner.github.io/EDI/reference/ordinal_gcomp_post_fit_cpp.md) : Fast G-Computation (Standardization) Point Estimate and Model-Based Inference for a Proportional-Odds Ordinal Model (C++) - [`get_ordinal_regression_hessian_cpp()`](https://kapelner.github.io/EDI/reference/get_ordinal_regression_hessian_cpp.md) : Proportional-Odds Ordinal Regression Hessian, Standalone (C++) - [`get_ordinal_regression_score_cpp()`](https://kapelner.github.io/EDI/reference/get_ordinal_regression_score_cpp.md) : Proportional-Odds Ordinal Regression Score, Standalone (C++) - [`get_stereotype_logit_hessian_cpp()`](https://kapelner.github.io/EDI/reference/get_stereotype_logit_hessian_cpp.md) : Stereotype Logit Regression Hessian, Standalone (C++) - [`get_stereotype_logit_score_cpp()`](https://kapelner.github.io/EDI/reference/get_stereotype_logit_score_cpp.md) : Compute Stereotype Logit Score ## Backend: Survival Regression Kernels - [`fast_coxph_regression()`](https://kapelner.github.io/EDI/reference/fast_coxph_regression.md) : Fast Cox Proportional Hazards Regression (R Wrapper) - [`fast_coxph_regression_cpp()`](https://kapelner.github.io/EDI/reference/fast_coxph_regression_cpp.md) : Fast Cox Proportional Hazards Regression, One-Shot Fit (C++ Backend) - [`fast_coxph_regression_prebuilt_cpp()`](https://kapelner.github.io/EDI/reference/fast_coxph_regression_prebuilt_cpp.md) : Fast Cox Proportional Hazards Regression, Cache-Reusing Fit (C++ Backend) - [`fast_weibull_regression()`](https://kapelner.github.io/EDI/reference/fast_weibull_regression.md) : Fast Weibull AFT Regression (R Wrapper: Rcpp Backend or survival) - [`build_cox_data_cache_cpp()`](https://kapelner.github.io/EDI/reference/build_cox_data_cache_cpp.md) : Build a Reusable Unstratified Cox Data Cache (C++ Backend) - [`build_stratified_cox_data_cache_cpp()`](https://kapelner.github.io/EDI/reference/build_stratified_cox_data_cache_cpp.md) : Build a Reusable Stratified Cox Data Cache (C++ Backend) - [`compute_coxph_rand_bootstrap_cpp()`](https://kapelner.github.io/EDI/reference/compute_coxph_rand_bootstrap_cpp.md) : Randomization/Bootstrap Reference Distribution of the Treatment Log-Hazard-Ratio for a Treatment-Only Cox PH Model (C++ Backend, Single-Covariate) - [`get_weibull_regression_general_hessian_cpp()`](https://kapelner.github.io/EDI/reference/get_weibull_regression_general_hessian_cpp.md) : Compute Weibull Regression Hessian (General Censoring) - [`get_weibull_regression_general_score_cpp()`](https://kapelner.github.io/EDI/reference/get_weibull_regression_general_score_cpp.md) : Compute Weibull Regression Score (General Censoring) ## Backend: Proportion/Beta Regression Kernels - [`fast_beta_regression()`](https://kapelner.github.io/EDI/reference/fast_beta_regression.md) : Fast Beta Regression (R Wrapper) - [`fast_beta_regression_with_var()`](https://kapelner.github.io/EDI/reference/fast_beta_regression_with_var.md) : Fast Beta Regression with Variance Calculation (R Wrapper) - [`get_beta_regression_hessian_cpp()`](https://kapelner.github.io/EDI/reference/get_beta_regression_hessian_cpp.md) : Beta Regression Hessian, Standalone (C++) - [`get_beta_regression_score_cpp()`](https://kapelner.github.io/EDI/reference/get_beta_regression_score_cpp.md) : Compute Beta Regression Score ## Backend: Matched-Design (Pocock-Simon) Assignment ## Backend: Math/Numeric Utilities Scalar/vectorized special-function kernels used throughout the package’s likelihoods; see vignette(“backend-contracts”). - [`logit()`](https://kapelner.github.io/EDI/reference/logit.md) : Logit (Log-Odds) Transform - [`inv_logit()`](https://kapelner.github.io/EDI/reference/inv_logit.md) : Inverse Logit (Logistic) Function - [`sample_mode()`](https://kapelner.github.io/EDI/reference/sample_mode.md) : Sample Mode - [`summary_glm_lean()`](https://kapelner.github.io/EDI/reference/summary_glm_lean.md) : Lean GLM Summary (Skips Deviance Residual Quantiles) ## Dispatch Policy Configuration Runtime-tunable policies governing optimizer choice, cold/warm-start heuristics, and parallel/serial dispatch across inference classes. See each get\_*/set\_* pair’s own documentation for the built-in defaults and override mechanism. - [`get_bootstrap_dispatch_policy()`](https://kapelner.github.io/EDI/reference/get_bootstrap_dispatch_policy.md) : Get the default bootstrap dispatch policy - [`get_cold_start_dispatch_policy()`](https://kapelner.github.io/EDI/reference/get_cold_start_dispatch_policy.md) : Get the default cold-start dispatch policy - [`get_optimization_dispatch_policy()`](https://kapelner.github.io/EDI/reference/get_optimization_dispatch_policy.md) : Get the default optimization dispatch policy - [`get_parallel_dispatch_policy()`](https://kapelner.github.io/EDI/reference/get_parallel_dispatch_policy.md) : Get the default parallel dispatch policy - [`get_warm_start_dispatch_policy()`](https://kapelner.github.io/EDI/reference/get_warm_start_dispatch_policy.md) : Get the default warm-start dispatch policy - [`set_cold_start_dispatch_policy()`](https://kapelner.github.io/EDI/reference/set_cold_start_dispatch_policy.md) : Update the cold-start dispatch policy - [`set_optimization_dispatch_policy()`](https://kapelner.github.io/EDI/reference/set_optimization_dispatch_policy.md) : Update the optimization dispatch policy - [`set_parallel_dispatch_policy()`](https://kapelner.github.io/EDI/reference/set_parallel_dispatch_policy.md) : Update the parallel dispatch policy - [`set_warm_start_dispatch_policy()`](https://kapelner.github.io/EDI/reference/set_warm_start_dispatch_policy.md) : Update the warm-start dispatch policy - [`set_num_cores()`](https://kapelner.github.io/EDI/reference/set_num_cores.md) : Set the number of cores for parallelization - [`unset_num_cores()`](https://kapelner.github.io/EDI/reference/unset_num_cores.md) : Unset the number of cores and stop parallel clusters ## Local Machine Tuning Benchmark this machine and persist machine-specific overrides for the performance-policy defaults above. See vignette(“reproducibility”)’s “Machine-dependent performance defaults” section. - [`tune_EDI_for_this_machine()`](https://kapelner.github.io/EDI/reference/tune_EDI_for_this_machine.md) : Benchmark this machine and tune EDI's performance-policy defaults to it - [`get_local_EDI_optimization()`](https://kapelner.github.io/EDI/reference/get_local_EDI_optimization.md) : Show this machine's saved EDI tuning, if any - [`clear_local_EDI_optimization()`](https://kapelner.github.io/EDI/reference/clear_local_EDI_optimization.md) : Delete this machine's saved EDI tuning and return to shipped defaults ## Miscellaneous Utilities - [`check_package_installed()`](https://kapelner.github.io/EDI/reference/check_package_installed.md) : Check Whether a Suggested Package Is Installed (Memoized) - [`create_model_matrix_from_features()`](https://kapelner.github.io/EDI/reference/create_model_matrix_from_features.md) : Build an Intercept-Free, Full-Rank Covariate Design Matrix from a Formula - [`edi_build_info_cpp()`](https://kapelner.github.io/EDI/reference/edi_build_info_cpp.md) : Return EDI Build Information (C++ Backend) - [`robust_negbinreg()`](https://kapelner.github.io/EDI/reference/robust_negbinreg.md) : Robust Negative Binomial Regression with Backward Column-Dropping Fallback - [`robust_survreg()`](https://kapelner.github.io/EDI/reference/robust_survreg.md) : Robust Parametric Survival Regression from Response/Censoring Vectors - [`robust_survreg_with_surv_object()`](https://kapelner.github.io/EDI/reference/robust_survreg_with_surv_object.md) : Robust Parametric Survival Regression (AFT) with Warm-Start and Random-Restart Fallback - [`toggle_asserts()`](https://kapelner.github.io/EDI/reference/toggle_asserts.md) : Toggle the execution of assertions throughout the package # Articles ### Package Concepts Cross-cutting reference material that individual class/function documentation links back into, rather than repeating inline. - [Notation Glossary](https://kapelner.github.io/EDI/articles/notation-glossary.md): - [Reproducibility: RNG and Seed Conventions](https://kapelner.github.io/EDI/articles/reproducibility.md): - [Backend Contracts: fast\_\* and C++ Utilities](https://kapelner.github.io/EDI/articles/backend-contracts.md): - [Validation Evidence](https://kapelner.github.io/EDI/articles/validation-evidence.md): - [Extending EDI with Your Own Inference and Design Classes](https://kapelner.github.io/EDI/articles/extending-edi.md): ### Cookbooks One complete, runnable design → assign → record → infer script per response type. Every chunk executes at build time; copy any one into a session and it works. Start with the continuous one, which narrates the shared four-step pattern the others follow. - [Cookbook: Continuous Outcome, End to End](https://kapelner.github.io/EDI/articles/cookbook-continuous.md): - [Cookbook: Incidence (Binary) Outcome, End to End](https://kapelner.github.io/EDI/articles/cookbook-incidence.md): - [Cookbook: Count Outcome, End to End](https://kapelner.github.io/EDI/articles/cookbook-count.md): - [Cookbook: Proportion Outcome, End to End](https://kapelner.github.io/EDI/articles/cookbook-proportion.md): - [Cookbook: Survival Outcome with Censoring, End to End](https://kapelner.github.io/EDI/articles/cookbook-survival.md): - [Cookbook: Ordinal Outcome, End to End](https://kapelner.github.io/EDI/articles/cookbook-ordinal.md): ### Ecosystem Where EDI sits among R’s experiment-design and inference packages, and how to try it without installing anything. - [How EDI Relates to randomizr, carat, coin, and Other Experiment-Design Packages](https://kapelner.github.io/EDI/articles/relation-to-other-packages.md): - [Try EDI in Your Browser (webR) — No Installation Needed](https://kapelner.github.io/EDI/articles/try-edi-in-your-browser.md):