Package: vimp 2.3.8

vimp: Perform Inference on Algorithm-Agnostic Variable Importance

Calculate point estimates of and valid confidence intervals for nonparametric, algorithm-agnostic variable importance measures in high and low dimensions, using flexible estimators of the underlying regression functions. For more information about the methods, please see Williamson et al. (Biometrics, 2020), Williamson et al. (JASA, 2021), and Williamson and Feng (ICML, 2020).

Authors:Brian D. Williamson [aut, cre], Jean Feng [ctb], Charlie Wolock [ctb], Noah Simon [ths], Marco Carone [ths]

vimp_2.3.8.tar.gz
vimp_2.3.8.zip(r-4.7)vimp_2.3.8.zip(r-4.6)vimp_2.3.8.zip(r-4.5)
vimp_2.3.8.tgz(r-4.6-any)vimp_2.3.8.tgz(r-4.5-any)
vimp_2.3.8.tar.gz(r-4.7-any)vimp_2.3.8.tar.gz(r-4.6-any)
vimp_2.3.8.tgz(r-4.6-emscripten)
manual.pdf |manual.html✨
DESCRIPTION |NEWS
card.svg |card.png
vimp/json (API)

# Install 'vimp' in R:
install.packages('vimp', repos = c('https://bdwilliamson.r-universe.dev', 'https://cloud.r-project.org'))

Bug tracker:https://github.com/bdwilliamson/vimp/issues

Pkgdown/docs site:https://bdwilliamson.github.io

Datasets:
  • vrc01 - Neutralization sensitivity of HIV viruses to antibody VRC01

On CRAN:

Conda:

machine-learningnonparametric-statisticsstatistical-inferencevariable-importance

8.16 score 24 stars 1 packages 71 scripts 701 downloads 1 mentions 47 exports 45 dependencies

Last updated from:c160a9fe05. Checks:7 NOTE, 2 OK. Indexed: yes.

TargetResultTimeFilesSyslog
linux-devel-x86_64NOTE189
source / vignettesOK320
linux-release-x86_64NOTE184
macos-release-arm64NOTE124
macos-oldrel-arm64NOTE136
windows-develNOTE133
windows-releaseNOTE127
windows-oldrelNOTE134
wasm-releaseOK120

Exports:average_vimbootstrap_secheck_fitted_valuescheck_inputscreate_zcv_vimest_predictivenessest_predictiveness_cvestimateestimate_nuisancesextract_sampled_split_predictionsget_cv_sl_foldsget_full_typeget_test_setmake_foldsmake_kfoldmeasure_accuracymeasure_anovameasure_aucmeasure_average_valuemeasure_cross_entropymeasure_deviancemeasure_msemeasure_npvmeasure_ppvmeasure_r_squaredmeasure_sensitivitymeasure_specificitymerge_vimpredictiveness_measureprocess_arg_lstrun_slsample_subsetsscale_estsp_vimspvim_icsspvim_sevimvimp_accuracyvimp_anovavimp_aucvimp_civimp_deviancevimp_hypothesis_testvimp_regressionvimp_rsquaredvimp_se

Dependencies:bitopsbootcaToolsclicodetoolscpp11cvAUCdata.tabledigestdplyrforeachfurrrfuturegamgenericsglobalsgluegplotsgtoolsiteratorsKernSmoothlifecyclelistenvmagrittrMASSnnlsparallellypillarpkgconfigpurrrR6rlangROCRrsamplesliderstringistringrSuperLearnertibbletidyrtidyselectutf8vctrswarpwithr

Introduction to vimp
Introduction | Installation | Quick Start | Detailed guide | A look at the VRC01 data | A first approach: linear regression | Building a library of learners | Estimating variable importance for a single variable | Estimating variable importance for a group of variables | Types of population variable importance | References
Rendered fromintroduction-to-vimp.Rmdusingknitr::rmarkdown

Last update: 2025-02-12
Started: 2020-06-23

Using precomputed regression function estimates in vimp
Introduction | Using precomputed regression function estimates without cross-fitting | A first approach: linear regression | Estimating variable importance for a single variable using precomputed regression function estimates | Estimating variable importance for a group of variables using precomputed regression function estimates | Conclusion | References
Rendered fromprecomputed-regressions.Rmdusingknitr::rmarkdown

Last update: 2025-02-12
Started: 2020-06-23

Variable importance with coarsened data
Introduction | Coarsened data in vimp | Example with missing outcomes | Example with two-phase sampling | References
Rendered fromipcw-vim.Rmdusingknitr::rmarkdown

Last update: 2025-02-12
Started: 2022-03-31

Types of VIMs
Introduction | Conditional VIMs | Marginal VIMs | Shapley VIMs | Adjusting for confounders | Conclusion | References
Rendered fromtypes-of-vims.Rmdusingknitr::rmarkdown

Last update: 2021-08-03
Started: 2020-06-23

Readme and manuals

Help Manual

Help pageTopics
Average multiple independent importance estimatesaverage_vim
Compute bootstrap-based standard error estimates for variable importancebootstrap_se
Check pre-computed fitted values for call to vim, cv_vim, or sp_vimcheck_fitted_values
Check inputs to a call to vim, cv_vim, or sp_vimcheck_inputs
Create complete-case outcome, weights, and Zcreate_z
Nonparametric Intrinsic Variable Importance Estimates and Inference using Cross-fittingcv_vim
Estimate a nonparametric predictiveness functionalest_predictiveness
Estimate a nonparametric predictiveness functional using cross-fittingest_predictiveness_cv
Estimate a Predictiveness Measureestimate
Estimate projection of EIF on fully-observed variablesestimate_eif_projection
Estimate nuisance functions for average value-based VIMsestimate_nuisances
Estimate Predictiveness Given a Typeestimate_type_predictiveness
Obtain a Point Estimate and Efficient Influence Function Estimate for a Given Predictiveness Measureestimate.predictiveness_measure
Extract sampled-split predictions from a CV.SuperLearner objectextract_sampled_split_predictions
Format a 'predictiveness_measure' objectformat.predictiveness_measure
Format a 'vim' objectformat.vim
Get a numeric vector with cross-validation fold IDs from CV.SuperLearnerget_cv_sl_folds
Obtain the type of VIM to estimate using partial matchingget_full_type
Return test-set only dataget_test_set
Create Folds for Cross-Fittingmake_folds
Turn folds from 2K-fold cross-fitting into individual K-fold foldsmake_kfold
Estimate the classification accuracymeasure_accuracy
Estimate ANOVA decomposition-based variable importance.measure_anova
Estimate area under the receiver operating characteristic curve (AUC)measure_auc
Estimate the average value under the optimal treatment rulemeasure_average_value
Estimate the cross-entropymeasure_cross_entropy
Estimate the deviancemeasure_deviance
Estimate mean squared errormeasure_mse
Estimate the positive predictive value (NPV)measure_npv
Estimate the positive predictive value (PPV)measure_ppv
Estimate R-squaredmeasure_r_squared
Estimate the sensitivitymeasure_sensitivity
Estimate the specificitymeasure_specificity
Merge multiple 'vim' objects into onemerge_vim
Construct a Predictiveness Measurepredictiveness_measure
Print 'predictiveness_measure' objectsprint.predictiveness_measure
Print 'vim' objectsprint.vim
Process argument list for Super Learner estimation of the EIFprocess_arg_lst
Run a Super Learner for the provided subset of featuresrun_sl
Create necessary objects for SPVIMssample_subsets
Return an estimator on a different scalescale_est
Shapley Population Variable Importance Measure (SPVIM) Estimates and Inferencesp_vim
Influence function estimates for SPVIMsspvim_ics
Standard error estimate for SPVIM valuesspvim_se
Nonparametric Intrinsic Variable Importance Estimates and Inferencevim
Nonparametric Intrinsic Variable Importance Estimates: Classification accuracyvimp_accuracy
Nonparametric Intrinsic Variable Importance Estimates: ANOVAvimp_anova
Nonparametric Intrinsic Variable Importance Estimates: AUCvimp_auc
Confidence intervals for variable importancevimp_ci
Nonparametric Intrinsic Variable Importance Estimates: Deviancevimp_deviance
Perform a hypothesis test against the null hypothesis of delta importancevimp_hypothesis_test
Nonparametric Intrinsic Variable Importance Estimates: ANOVAvimp_regression
Nonparametric Intrinsic Variable Importance Estimates: R-squaredvimp_rsquared
Estimate variable importance standard errorsvimp_se
Neutralization sensitivity of HIV viruses to antibody VRC01vrc01