The aim of this document is to keep track of the changes made to the
different versions of the R package
pencal.
The numbering of package versions follows the convention a.b.c, where a and b are non-negative integers, and c is a positive integer. When minor changes are made to the package, a and b are kept fixed and only c is increased. Major changes to the package, instead, are made apparent by changing a or b.
Each section of this document corresponds to a major change in the package - in other words, within a section you will find all those package versions a.b.x where a and b are fixed whereas x = 1, 2, 3, … Each subsection corresponds to a specific package version.
prepare_longdata is not a
dataframelcmm that broke the examples have been fixedrun = FALSE) to examples in
?fit_mlpmms, ?summarize_mlpmms and
?fit_prcmlpmm: some changes have been introduced in
lcmm version 2.2.0 which make the example with
fit_mlpmms break. It’s unclear why this is happening, and
it may take some time until the problem is solved. Until the source of
the problem is found, the examples for the PRC MLPMM approach may fail
to work. The PRC LMM approach is still completely functional.getlmm and getmlpmm functions have been
replaced by two S3 classes with summary
methodssummary methods added for the output of
steps 2summary methods for step
3fitted_prclmm and fitted_prcmlpmm objects
have been refittedsurvplot_prc functionlandmark argument to
simulate_prclmm_data and
simulate_prcmlpmm_data. Examples updated accordingly and
refitted fit_prclmm and fit_prcmlpmmsurvpred_prclmm,
survpred_prcmlpmm, performance_pencox and
performance_pencoxperformance_prc and
performance_pencox_baselinemetric argument to performance_prc
and performance_pencox_baselinefit_prclmm and fit_prcmlpmm
objects so they are up to date with classes and methodspencox_baseline to pencox and
performance_pencox_baseline to
performance_pencoxpbc2data and corresponding documentationCITATION file using bibentry( ) to
address CRAN noteDESCRIPTION file (added biocViews:
to fix survcomp installation problems)LICENSE filesummarize_lmms and
summarize_mlpmms (this should yield computing time gains
with thousands of longitudinal predictors)prclmm and prcmlpmm) and
corresponding methods (print and summary) to
the packagegetlmm and
getmlpmmcontrol argument to fit_lmms. This
argument is used to pass control parameters to nlme::lme
(see ?nlme::lmeControl). See ?fit_lmms for the
defaultssimulate_prclmm_data now outputs an extra element
(theta.true) containing the true parameters used to
generate the dataeval( ) when creating baseline.covs
within survpred_prclmm and
survpred_prcmlpmmseed argument to fit_lmms and
fit_mlpmmssummarize_lmms in case estimation of
a LMM fails for a bootstrap replicatepfac.base.covs in fit_prclmmsurvpred_prclmm when
new.longdata is provided. From this version, when all
observations of a longitudinal predictor for a given subject are
missing, a warning is produced and the corresponding random effects are
set equal to 0 (population average). Previously, the function returned
an error due to the NAsstandardize argument in
documentation of pencox_baselineperformance_prc and
performance_pencox_baseline extended to computations of
naive tdAUC performancemax.ymissing argument to fit_lmms:
with this change, it is now possible to estimate the LMMs within the
PRC-LMM model even if there are subjects with missing measurements for
some (but not all) of the longitudinal outcomes. Within
summarize_lmms, the predicted random effects when a
longitudinal outcome is missing for a given subject are set = 0
(marginal / population average). Setting max.ymissing = 0
disables such additional featuresummarize_lmms on subjects without
any longitudinal information available (i.e., 100% missing on all
longitudinal variables used in step 1)purrr (now required by
summarize_lmms)CRAN dependency issue with examples in
simulate_prclmm_data and
simulate_prcmlpmm_datatau.age argument to
simulate_prclmm_data and
simulate_prclmm_datafit_lmms (row
181)survpred_prclmmsurvpred_prclmm fail when new data
for just 1 subject were supplied (added missing
drop = FALSE)survpred_prcmlpmmsurvpred_prc replaced by two distinct
functions: survpred_prclmm for the PRC-LMM model, and
survpred_prcmlpmm for the PRC-MLPMM modelfit_lmms is now more memory efficient
(keep.data = F when calling lme)fit_mlpmms is now faster (parallelization implemented
also before the CBOCP is started)pencox_baseline and
performance_pencox_baselineT with
TRUE)simulate_prcmlpmm_data, fit_mlpmms,
summarize_mlpmms and fit_prcmlpmmperformance_prclmm to
performance_prc, and survpred_prclmm to
survpred_prc (the functions work both for the PRC-LMM, and
the PRC-MLPMM)survpred_prclmm, which computes
predicted survival probabilities from the fitted PRC-LMM modelfitted_prclmm data object and related
documentation (it is used in the examples of
performance_prclmm)pencal package.
It comprises the skeleton around which the rest of the R package will be
builtsimulate_t_weibull and
simulate_prclmm_data);fit_lmms,
summarize_lmms and fit_prclmm);performance_prclmm)R package that is user-friendly,
comprehensive and well-documented is an effort that takes months,
sometimes even years. This package is currently under active
development, and many additional features and functionalities
(including vignettes!) will be added incrementally with the next
releases. If you notice a bug or something unclear in the documentation,
feel free to get in touch with the maintainer of the package!