NEWS | R Documentation |
NEWS file for the tram package
Changes in Version 1.1-2 (2024-10-02)
Gradient check failed on Fedora noLD.
Changes in Version 1.1-1 (2024-09-27)
Gradient check failed on MacOS.
Changes in Version 1.1-0 (2024-09-24)
mmlt
moved to mlt 1.6-0.New
Mmlt
allowing arbitrary mixes of continuous and discrete data, including exact and censored observations for the same variable; implementing three (potentially) convex approximations; allowing for non-informative missings encoded as-Inf, Inf
.Compris
now also uses the parametric likelihood for the competing risk case.Allow density predictions for all continuous variables (regardless of censoring in training data).
Changes in Version 1.0-5 (2024-08-17)
Add example for
Compris
.Correct
simulate.mmlt
.Change to
R\_Calloc
and friends.
Changes in Version 1.0-4 (2024-05-13)
Allow larger then needed
args$w
argument inmmlt
.Fix bug in
predict.mmlt
.
Changes in Version 1.0-3 (2024-04-15)
Add sequential fits to
mmlt
.Add
fixed = TRUE/FALSE
argument tocoef.mmlt
such that the whole parameter vector can be retrieved.Handle constraints for fixed parameters in
mmlt
correctly (asmlt
always did).tram
andPolr
allow binary responses (and return results identical toglm
with appropriatefamily
).
Changes in Version 1.0-2 (2024-01-30)
New
demo("survtram")
anddemo("hcc")
.predict
methods fortram
andstram
now offer the sametype
argument asmlt::predict.ctm
offers.
Changes in Version 1.0-1 (2023-12-18)
Allow shift-scale transformation models in
mmlt
.Add nonparametric log-likelihood to
Compris
.
Changes in Version 1.0-0 (2023-08-25)
Improved, simplified, and generalised implementation of
mmlt
.Coxph
,Colr
, andBoxCox
allow unbiased estimation of time-to-event distributions under dependent censoring.All
tram
models can be equipped with frailty terms.Fix some minor issues.
Changes in Version 0.8-2 (2023-03-28)
Update demo
stram
.
Changes in Version 0.8-1 (2023-03-09)
Add
simulate.mmlt
.Survreg
didn't work with constraints, reported by Lucas Kook.mtram
didn't deal properly with interval censoring in all cases.Enable stratification for shift-scale transformation models (still experimental).
Fix S3 argument issues.
Try to detect negative SEs.
Changes in Version 0.8-0 (2022-11-02)
Stabilise and generalise
mmlt
: Alternative link functions, separate lower triangular matrix storage and computations frommmlt
.coef(<mmlt>, type = "Sigma")
andcoef(<mmlt>, type = "Corr")
were incorrect for more than three dimensions.Improved numerical stability in
mtram
.
Changes in Version 0.7-2 (2022-08-05)
New location-scale functionality, see
demo("stram")
.New Laplace link function.
New cauchit link function.
Changes in Version 0.7-1 (2022-05-18)
Minor bug fixed for shift-scale transformation models (still experimental).
bread.tram
added forsandwich
to work.Update
mtram
vignette; move code to demo.
Changes in Version 0.7-0 (2022-04-01)
Add shift-scale transformation models (experimental).
Add methods for probabilistic indices and overlap coefficients + friends.
Export
Gradient
andHessian
methods.Simplify
score_test
andprofile
: Usefixed
instead ofoffset
.Models with standardisation now available in
mtram
for exact continuous outcomes and link functions other than probit.
Changes in Version 0.6-4 (2022-01-14)
Remove arguments ignored by
mlt
.Move mtram vignette code to demo as it took too long on Windows for CRAN.
Changes in Version 0.6-3 (2022-01-04)
Deal with stratum - covariate interactions, overparameterised coefficients are constraint to zero.
Changes in Version 0.6-2 (2021-10-19)
Make sure to use the Schur complement when computing variances in for linear transformation models in
score_test
andperm_test
.Fix LaTeX problems.
Changes in Version 0.6-1 (2021-09-16)
Add
dofit
argument tommlt
.Robustify
vcov
formmlt
objects.Add experimental
score_test
andperm_test
methods forglm
.
Changes in Version 0.6-0 (2021-03-08)
Add
simulate
method.Enable nonparametric likelihood estimation by
Polr
.New argument
sparse_nlevels
totram
, requesting a modelMatrix
for ordered factors with at leastsparse_nlevels
levels.
Changes in Version 0.5-2 (2020-10-23)
Add experimental
score_test
andperm_test
forsurvival::coxph
.Update simulation code.
Changes in Version 0.5-1 (2020-09-03)
Robustify computation of score intervals.
Add Spearman correlation to
mmlt
example.
Changes in Version 0.5-0 (2020-08-27)
Lehmann()
parameter is now labelled as proportional reverse time hazard ratio.Add
mmlt
for multivariate conditional transformation models (continuous responses only for now).Reproducibility material for <arxiv:1906.03151> added to package.
Changes in Version 0.4-0 (2020-05-11)
Force support to start at time zero and constrain cumulative hazard to zero for time zero in
Aareg
.
Changes in Version 0.4-0 (2020-05-11)
Add
Aareg
for Aalen additive hazard models.
Changes in Version 0.3-3 (2020-01-16)
score_test
generic and method added for computing score tests and corresponding confidence intervals.perm_test
generic and method added for computing permutation score tests.PI
converts log-odds ratios to probabilistic indices and vice versa.
Changes in Version 0.3-2 (2020-01-08)
profile
method added for computing profile likelihood confidence intervals.Allow additional linear inequality constraints for regression coefficients.
Changes in Version 0.3-1 (2019-11-05)
Bugfixes
Fix problem in C header file.
Fix problems with responses of class
R
, spotted by Balint Tamasi.
Changes in Version 0.3-2 (2019-12-02)
Add new demo.
Bugfixes
Deal with
model_only
inSurvreg
, spotted by Balint Tamasi.
Changes in Version 0.3-0 (2019-10-09)
Bugfixes
y | s1:s2 ~ x
lead to rank-deficit models, the intercept is now removed.Not really a bug, but time-consuming examples were removed (or replaced by static output) in package vignettes to make CRAN happy.
as.mlt
returned an object of classmlt
but notmlt_fit
.
New Features
New marginally interpretable models for clustered data in
mtram
, seemtram
vignette. This is still experimental and very rough, so please be careful.Compute
vcov.tram
via Schur complement when possible.
Changes in Version 0.2-6 (2019-06-20)
Add regression test for count data and
log_first = TRUE
.
Changes in Version 0.2-5 (2019-02-25)
tram
objects are now in line withmultcomp::glht
, allowing post-hoc multiple comparisons.
Changes in Version 0.2-4 (2019-01-22)
log_first = TRUE
is now accepted bytram
and all model functions callingtram
. This is still experimental.Silence regression tests on Windows.
Changes in Version 0.2-3 (2018-09-17)
New
extrapolate = TRUE
option for all models constraints the second derivate of the Bernstein transformation function to be zero atsupport
. This helps to get rid of possible discontinuous densities atsupport
.Add
Lehmann
for fitting shift transformation models those linear predictor can be interpreted as log-Lehmann-alternative.Add
method = "loglog"
toPolr
.New
update
method.
Changes in Version 0.2-2 (2018-06-22)
Use default
bounds = c(0, Inf)
forSurv
objects (for example inCoxph
.Update to mlt 1.0-2.
Changes in Version 0.2-1 (2018-04-20)
Likelihood ratio tests with fixed parameters gave an error.
Remove strata from linear predictor (experimental).
Try to implement a better guess for the
add
argument later defining the axes corresponding to the response in plots.All models accept
add
andbounds
arguments.
Changes in Version 0.2-0 (2018-02-25)
tram first published on CRAN.