Package: FlexRL 1.0.1

Kayané ROBACH

FlexRL: Flexible Record Linkage and Linked Data Quality Assessment

Probabilistically link records that refer to the same entities across two data sources without a unique identifier, using partially identifying variables such as product code, brand, category, birth year, sex or postal code. 'FlexRL' implements a Stochastic Expectation Maximisation (StEM) approach to Record Linkage (Robach et al., 2025, <doi:10.1093/jrsssc/qlaf016>). The model accounts for registration errors (missing values and mistakes) and for variables that change over time, enforces one-to-one assignment, and has a low memory footprint. The package also provides tools for inference on linked data: two estimators of the false discovery proportion of a linkage (Robach et al., 2025, <doi:10.1002/sim.70292>), based on linkage scores and on synthetic data, and diagnostics comparing the linked sample with the source data. These tools also apply on the linkage output of other record linkage packages.

Authors:Kayané ROBACH [aut, cre, cph], Michel H. HOF [aut, cph]

FlexRL_1.0.1.tar.gz
FlexRL_1.0.1.zip(r-4.7-x86_64)FlexRL_1.0.1.zip(r-4.7-arm64)FlexRL_1.0.1.zip(r-4.6-x86_64)FlexRL_1.0.1.zip(r-4.6-arm64)FlexRL_1.0.1.zip(r-4.5-x86_64)
FlexRL_1.0.1.tgz(r-4.6-x86_64)FlexRL_1.0.1.tgz(r-4.6-arm64)FlexRL_1.0.1.tgz(r-4.5-x86_64)FlexRL_1.0.1.tgz(r-4.5-arm64)
FlexRL_1.0.1.tar.gz(r-4.7-arm64)FlexRL_1.0.1.tar.gz(r-4.7-x86_64)FlexRL_1.0.1.tar.gz(r-4.6-arm64)FlexRL_1.0.1.tar.gz(r-4.6-x86_64)
FlexRL_1.0.1.tgz(r-4.6-emscripten)
manual.pdf |manual.html✨
DESCRIPTION |NEWS
card.svg |card.png
FlexRL/json (API)

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

Bug tracker:https://github.com/robachowyk/flexrl/issues

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

Uses libs:
  • c++– GNU Standard C++ Library v3

On CRAN:

Conda:

cpp

5.26 score 1 stars 13 scripts 424 downloads 31 exports 142 dependencies

Last updated from:77daff87be. Checks:15 OK. Indexed: yes.

TargetResultTimeFilesSyslog
linux-devel-arm64OK163
linux-devel-x86_64OK203
source / vignettesOK273
linux-release-arm64OK161
linux-release-x86_64OK168
macos-release-arm64OK157
macos-release-x86_64OK310
macos-oldrel-arm64OK168
macos-oldrel-x86_64OK251
windows-devel-arm64OK227
windows-devel-x86_64OK212
windows-release-arm64OK299
windows-release-x86_64OK169
windows-oldrel-x86_64OK164
wasm-releaseOK144

Exports:compute_augmRL_FDP_synthcompute_RL_FDP_scorecreate_data_alphaFDP_scoreFDP_synthlink_with_BRLlink_with_diyarlink_with_fastLinklink_with_fedmatchlink_with_FlexRLlink_with_multilinklink_with_reclin2log_liklog_possible_configmmdnaive_linkageplot_distributionsplot_linkage_scoresplot_StEM_convergenceprepare_dataprop_levelRL_agreementRL_diagnosticssimulate_datasimulateDsimulateHsmdStEMsupport_iousurvival_modelsynthesise

Dependencies:adagioarfbackportsBHbitbit64blobbootBRLbromanbroomcachemclassclassIntclicliprcmmcodetoolscoincpp11crayondata.tableDBIdiagramdigestdiyardoParalleldplyre1071evdfarverfastLinkfastmapfedmatchffforcatsforeachforeignfuturefuture.applygenericsgeosphereggplot2glmnetglobalsgluegtablegtoolshavenhmsigraphipredisobanditeratorsjomoKernSmoothlabelinglatticelavalibcoinlifecyclelistenvlme4lpSolvemagrittrMASSMatrixmatrixStatsmcclustmemoisemiceminqamipfpmitmlmodeltoolsmultcompmultilinkmvtnormnlmenloptrnnetnumDerivordinalpanparallellypartypillarpkgconfigplotrixplyrpolsplineprettyunitsprodlimprogressprogressrprotoproxypurrrR6randomForestrangerrbibutilsRColorBrewerRcppRcppArmadilloRcppEigenRdpackreadrreclin2RecordLinkagereformulasrlangrmutilrpartRsolnpRSQLiteS7sandwichscalesshapeSnowballCSQUAREMstringdiststringistringrstrucchangesurvivalsynthpopTH.datatibbletidyrtidyselecttruncnormtzdbucminfutf8vctrsviridisLitevroomwithrxtablezoo

Scalable Record Linkage with FlexRL
One pipeline for all the wrappers | Regional subset of the NLTCS data | Full SHIW data | Loop over the regions of the SHIW data with blocking
Rendered fromFlexRL-RL-block-vignette.Rmdusingknitr::rmarkdown

Last update: 2026-10-14
Started: 2026-10-05

Record Linkage with FlexRL
Rendered fromFlexRL-RL-vignette.Rmdusingknitr::rmarkdown

Last update: 2026-10-14
Started: 2026-09-18

FlexRL-RL-block-vignette
One pipeline for all the wrappers | Regional subset of the NLTCS data | Regional subset of the SHIW data | Full SHIW data | Loop over the regions of the SHIW data with blocking
Rendered fromOLDFlexRL-RL-block-vignette.Rmdusingknitr::rmarkdown

Last update: 2026-10-12
Started: 2026-10-12

FlexRL-RL-vignette
Rendered fromOLDFlexRL-RL-vignette.Rmdusingknitr::rmarkdown

Last update: 2026-10-12
Started: 2026-10-12

Readme and manuals

Help Manual

Help pageTopics
Estimate the false discovery proportion of a record-linkage method via synthetic augmentationcompute_augmRL_FDP_synth
Estimate the false discovery proportion of a record-linkage method via model specific linkage scorescompute_RL_FDP_score
Book-keeping data frame for parameters of PIVs dynamicscreate_data_alpha
Model specific, linkage score based, false discovery proportion at a given thresholdFDP_score
Model agnostic, based on synthetic data, false discovery proportion at a given thresholdFDP_synth
FlexRL: A Flexible Model for Record LinkageFlexRL-package FlexRL
Run BRL through the uniform wrapper interfacelink_with_BRL
Run diyar through the uniform wrapper interfacelink_with_diyar
Run fastLink through the uniform wrapper interfacelink_with_fastLink
Run fedmatch through the uniform wrapper interfacelink_with_fedmatch
Run FlexRL through the uniform wrapper interfacelink_with_FlexRL
Run multilink through the uniform wrapper interfacelink_with_multilink
Run reclin2 through the uniform wrapper interfacelink_with_reclin2
Log-likelihood of the linkage matrixlog_lik
Log number of possible linkage configurationslog_possible_config
Maximum Mean Discrepancy between two sets of variablesmmd
Naive (deterministic exact-match) record linkagenaive_linkage
Compare distributions of shared variables across data sets (histograms/barplots)plot_distributions
Plot the distribution of linkage scoresplot_linkage_scores
Monte Carlo convergence (trace) plots for a fitted StEM modelplot_StEM_convergence
Plot post-linkage diagnostics over thresholdsplot.discrepancy_curves
Plot FDP estimates against the linkage decision thresholdplot.FDP_curves
Plot post-linkage diagnosticsplot.RL_diagnostics
Prepare two data sources for 'StEM()'prepare_data
Print post-linkage diagnosticsprint.RL_diagnostics
Proportion of a data set with a given variable at a given levelprop_level
Agreement rate of pairs on shared variablesRL_agreement
Post-linkage diagnosticsRL_diagnostics
Simulate two linked data sources for record linkage benchmarkingsimulate_data
Simulate the linkage matrix DsimulateD
Simulate the true PIV values underlying the registered recordssimulateH
Standardised mean difference between a selected set and a baselinesmd
Stochastic Expectation-Maximisation for record linkageStEM
Intersection-over-union of two histogram supportssupport_iou
Survival models for the dynamics of a PIVsurvival_model
Augment file B with synthetic recordssynthesise