The Visual predictive checks (VPC) shown below are only intended to
demonstrate the various options available in xpose and should not be
used as reference for modeling practice. Furthermore, the plots are only
based on 20 simulations to minimize the computing time of the examples,
the size of the
xpdb_ex_pk object and of the xpose package
VPC can be created either by:
The VPC computing and plotting parts have been separated into two
respectively. This allows to:
The generated VPC data is stored in the xpdb under specials datasets and can be used later on.
run001.lst overview: - Software: nonmem 7.3.0 - Attached files (memory usage 1.6 Mb): + obs tabs: $prob no.1: catab001.csv, cotab001, patab001, sdtab001 + sim tabs: $prob no.2: simtab001.zip + output files: run001.cor, run001.cov, run001.ext, run001.grd, run001.phi, run001.shk + special: vpc continuous (#3) - gg_theme: theme_readable - xp_theme: theme_xp_default - Options: dir = data, quiet = FALSE, manual_import = NULL
Multiple VPC data can be stored in an xpdb, but only one of each
vpc_typeallows to specify the type of VPC to be computed: “continuous” (default), “categorical”, “censored”, “time-to-event”.
stratifyoptions defines up to two stratifying variable to be used when computing the VPC data. The
stratifyvariables can either be provided as a character vector (
stratify = c('SEX', 'MED1')) or a formula (
stratify = SEX~MED1) . The former will result in the use of
ggforce::facet_wrap_paginate()and the latter of
ggforce::facet_grid_paginate()when creating the plot. With “categorical” VPC the “group” variable will also be added by default.
optargument expects the output from the
vpc_typeworks similarly to
vpc_data()and is only required if several VPC data are associated with the xpdb.
smooth = TRUE/FALSEallows to switch between smooth and squared shaded areas.
line_linetypeeach require three values for the low, median and high percentiles respectively.
To create VPC using the xpdb data, at least one simulation and one
estimation problem need to present. Hence in the case of NONMEM the run
used to generate the xpdb should contain several
vpc_data() the problem number can be specified for the
obs_problem) and the simulation
sim_problem). By default xpose picks the last one of each
to generate the VPC.
run001.lst overview: - Software: nonmem 7.3.0 - Attached files (memory usage 1.5 Mb): + obs tabs: $prob no.1: catab001.csv, cotab001, patab001, sdtab001 + sim tabs: $prob no.2: simtab001.zip + output files: run001.cor, run001.cov, run001.ext, run001.grd, run001.phi, run001.shk + special: <none> - gg_theme: theme_readable - xp_theme: theme_xp_default - Options: dir = data, quiet = FALSE, manual_import = NULL
vpc_data() contains an argument
psn_folder which can be used to point to a PsN generated VPC
folder. As in most xpose function
can be used to automatize the process
psn_folder = '@dir/@run_vpc' where
@run will be automatically translated to initial
(i.e. when the xpdb was generated) run directory and run number
In this case, the data will be read from the
m1.zip if compressed). Note that PsN drops unused
columns to reduce the simtab file size. Thus, in order to allow for more
flexibility in R, it is recommended to use multiple stratifying
-stratify_on=VAR1,VAR2) and the prediction
-predcorr adds the PRED column to the output)
options in PsN to
avoid having to rerun PsN to add these
variables later on. In addition,
-stratify_on PsN options are
automatically applied to xpose VPC.
The PsN generated binning can also applied to xpose VPC with the
psn_bins = TRUE (disabled by
default). However PsN and the vpc
package work slightly differently so the results may not be optimal and
the output should be evaluated carefully.