Age | Commit message (Collapse) | Author | Files | Lines |
|
|
|
|
|
In particular, adapt the display of parameter boxplots
for saem fits using mkin transformations to the way
used for saem fits using saemix transformations, i.e.
always show parameters on the natural scale, and normalised them by
dividing by the median from the multiple runs.
|
|
- Split out llhist and parhist documentation
- Add example code for multistart
- Create a multistart vignette, because the example code fails when run
by pkgdown
- Fix multistart for the case of mkin transformations in the saem fit
|
|
|
|
|
|
We now directly import from rlang and vctrs, which were indirect
dependencies anyways. purrr::map_dfr is deprecated in the upcoming purrr
1.0, and depends on dplyr (since when?) which is only suggested by
purrr. This would lead new installations of mkin to fail if dplyr is not
installed as well.
|
|
|
|
|
|
|
|
|
|
|
|
- 'R/mhmkin.R': New method for performing multiple hierarchical mkin fits in one function call, optionally in parallel.
- 'R/saem.R': 'logLik' and 'update' methods for 'saem.mmkin' objects.
- 'R/illparms.R': Add methods for 'saem.mmkin' and 'mhmkin' objects.
tests: Use 2 cores on travis, should work according to docs
|
|
|
|
Also, support FOMC with saemix transformations
|
|
|
|
Also, add a method for gathering convergence information
and a method for gathering information on ill-defined parameters
|
|
|
|
|
|
Thanks to Tomas Kalibera for his analysis of the problem on the
r-package-devel mailing list and for the suggestion on how to
fix it. See the current benchmark vignette for the new data
on mkin 1.1.1 with R 4.2.1, with unprecedented performance.
|
|
Documentation and test results were updated, the latter with regard
to the previous work on plot.mixed.mmkin.
|
|
|
|
- New argument 'default_log_parms' for mean_degparms()
- 'plot.mixed.mmkin': Pass the frame argument also to residual plots,
take the 'default_log_parms' argument for 'mean_degparms' used for
constructing approximate population curves, plot population curve last
to avoid that it is covered by data
|
|
Also increase the performance a bit (from about 210 s to about 140 s in
the case of DFOP with four chains and 300, 100 iterations).
|
|
|
|
|
|
|
|
I am postponing my attempts to get the nlmixr interface to CRAN, given
some problems with nlmixr using R-devel under Windows, see
https://github.com/nlmixrdevelopment/nlmixr/issues/596
and
https://github.com/r-hub/rhub/issues/512,
which is fixed by the removal of nlmixr from the testsuite.
For the tests to be more platform independent, the biphasic mixed
effects models test dataset was defined in a way that fitting
should be more robust (less ill-defined).
|
|
|
|
|
|
|
|
|
|
|
|
|
|
By actually passing dot arguments (that can include fixed.estim) to
saemixModel, as advertised in the docs.
|
|
as obtained by mean_degparms(..., random = FALSE), instead
of the list obtained by mean_degparms(, ... random = TRUE) that
is passed by nlme.mmkin to nlme by default.
|
|
Respect digits argument when printing correlations in summaries
|
|
|
|
|
|
|
|
This avoids numerical instabilities that sometimes occur with the FOCEI
algorithm in nlmixr when the initial values are very close to the
optimum values
|
|
|
|
|
|
|
|
|
|
The EFSA URL failed on winbuilder because some cookie sets a different
domain, so I am now using \href{} with the full link as link text instead
of \url{}
|
|
The data given in previous mkin versions for "Borstel 2" (Staudenmaier
2013) are in fact a subset of the "Borstel 1" data, with the "Borstel 2"
data simply being further analysed for isomer composition by
Staudenmaier (2013).
While correcting this, the URL of the RAR published by EFSA was
updated, as the EFSA Register of Questions was replaced by the
Open EFSA portal.
This also affects the recent publication in "Environments" [1], where
these two datasets were pooled. However, the influence on the final
results can be expected to be minimal. Out of the 16 observations for
the Borstel soil, five were erroneously duplicated which just changes
the weight of the different sampling points and modifies the variance.
The conclusions of the publication are qualitative and are not
considered to be affected.
[1] https://doi.org/10.3390/environments8080071
|
|
Evaluations with nlme, saemix and nlmixr are included
|
|
|
|
|