Package: HQM 2.1

Dimitrios Bagkavos

HQM: Superefficient Estimation of Future Conditional Hazards Based on Marker Information

Provides univariate and indexed (multivariate) nonparametric smoothed kernel estimators for the future conditional hazard rate function when time-dependent covariates are present, a bandwidth selector for the estimator's implementation and pointwise and uniform confidence bands. Methods used in the package refer to Bagkavos, Isakson, Mammen, Nielsen and Proust-Lima (2025) <doi:10.1093/biomet/asaf008>.

Authors:Dimitrios Bagkavos [aut, cre], Alex Isakson [ctb], Enno Mammen [ctb], Jens Nielsen [ctb], Cecile Proust-Lima [ctb]

HQM_2.1.tar.gz
HQM_2.1.tar.gz(r-4.7-any)HQM_2.1.tar.gz(r-4.6-any)
HQM_2.1.tgz(r-4.6-emscripten)
manual.pdf |manual.html✨
DESCRIPTION
card.svg |card.png
HQM/json (API)

# Install 'HQM' in R:
install.packages('HQM', repos = c('https://cran.r-universe.dev', 'https://cloud.r-project.org'))
Datasets:
  • pbc2 - Mayo Clinic Primary Biliary Cirrhosis Data

On CRAN:

Conda:

This package does not link to any Github/Gitlab/R-forge repository. No issue tracker or development information is available.

1.48 score 532 downloads 49 exports 100 dependencies

Last updated from:7d3e4eaaab. Checks:4 OK. Indexed: yes.

TargetResultTimeFilesSyslog
linux-devel-x86_64OK202
source / vignettesOK211
linux-release-x86_64OK170
wasm-releaseOK167

Exports:auc.hqmb_selectionb_selection_index_optimb_selection_prep_gBoot.hqmBoot.hrandindex.parambs.hqmBwB.HRandIndex.paramcompute_iid_decompositioncompute_iid_decomposition_competing_riskscompute_iid_decomposition_survivalCompute.iid.KMConf_bandsdataset_splitdijEpang_xtget_alphaget_h_xget_h_xllh_xth_xt_vech_xtllindex_optimK_bK_b_matlin_interpolatellK_bmake_Nmake_Nimake_sfmake_Ymake_YiPivot.Index.CIsprep_bootprep_cvprep_cv2Q1Quantile.Index.CIsR_KSim.True.HazardSingleIndCondFutHazsn.0sn.1sn.2StudentizedBwB.Index.CIstimeROCto_idxK_b

Dependencies:backportsbase64encbslibcachemcheckmatecliclustercmprskcodetoolscolorspacecpp11data.tablediagramdigestdoParallelevaluatefarverfastmapfontawesomeforeachforeignFormulafsfuturefuture.applyggplot2glmnetglobalsgluegridExtragtablehighrHmischtmlTablehtmltoolshtmlwidgetsisobanditeratorsJMjquerylibjsonliteKernSmoothknitrlabelinglatticelavalifecyclelistenvmagrittrMASSMatrixMatrixModelsmemoisemetsmimemultcompmvtnormnlmennetnumDerivparallellypecplotrixpolsplineprodlimprogressrPublishquantregR6rangerrappdirsRColorBrewerRcppRcppArmadilloRcppEigenriskRegressionrlangrmarkdownrmsrpartrstudioapiS7sandwichsassscalesshapeSparseMSQUAREMstringistringrsurvivalTH.datatimeregtinytexvctrsviridisLitewithrxfunyamlzoo

Readme and manuals

Help Manual

Help pageTopics
AUC for the High Quality Marker estimatorauc.hqm
Cross validation bandwidth selectionb_selection
Cross validation index parameter selectionb_selection_index_optim
Preparations for bandwidth selectionb_selection_prep_g
Indexed HQM hazard estimator for one bootstrap sampleBoot.hqm
Bootstrap Estimation of Hazard Function and Index ParametersBoot.hrandindex.param
Brier score for the High Quality Marker estimatorbs.hqm
Bootstrap Estimation of Hazard Function and Index ParametersBwB.HRandIndex.param
IID decomposition for time-dependent AUC with IPCWcompute_iid_decomposition compute_iid_decomposition_competing_risks compute_iid_decomposition_survival
Compute.iid.KM function implementationCompute.iid.KM
Confidence bandsConf_bands
Split dataset for K-fold cross validationdataset_split
D matrix entries, used for the implementation of the local linear kerneldij
Epanechnikov kernelEpan
Computation of a key component for wild bootstrapg_xt
Marker-only hazard rateget_alpha
Local constant future conditional hazard rate estimatorget_h_x
Local linear future conditional hazard rate estimatorget_h_xll
Local constant future conditional hazard rate estimation at a single time pointh_xt
Hqm estimator on the marker gridh_xt_vec
Local linear future conditional hazard rate estimation at a single time pointh_xtll
Indexing parameter objective functionindex_optim
Classical (unmodified) kernel and related functionalsK_b K_b_mat xK_b
Linear interpolationlin_interpolate
Local linear kernelllK_b
Local linear weight functionssn.0 sn.1 sn.2
Occurance and Exposure on gridsmake_N make_Ni make_Y make_Yi
Survival function from a hazardmake_sf
Mayo Clinic Primary Biliary Cirrhosis Datapbc2 pbc2.id
Compute Pivot Pointwise Confidence Intervals for the Indexed Hazard Rate EstimatePivot.Index.CIs
Precomputation for wild bootstrapprep_boot
Prepare for Cross validation bandwidth selectionprep_cv
Prepare for Cross validation index parameter selectionprep_cv2
Bandwidth selection score Q1Q1
Compute Quantile Pointwise Confidence Intervals for for the Indexed Hazard Rate EstimateQuantile.Index.CIs
Bandwidth selection score RR_K
Simulated true hazard (bootstrap average)Sim.True.Hazard
Local linear future conditional hazard estimator (wrapper)SingleIndCondFutHaz
Compute Studentized Double Bootstrap Pointwise Confidence Intervals for the Indexed Hazard Rate EstimateStudentizedBwB.Index.CIs
Time-dependent ROC curve estimationtimeROC
Event data frameto_id