, Karl Brendel [ctb],
Thi Huyen Tram Nguyen [ctb], Marc Cerou [ctb], Romain Leroux
[ctb], France Mentre [ctb]| Title: | Normalised Prediction Distribution Errors for Nonlinear Mixed-Effect Models |
|---|---|
| Description: | Provides routines to compute normalised prediction distribution errors, a metric designed to evaluate non-linear mixed effect models such as those used in pharmacokinetics and pharmacodynamics. |
| Authors: | Emmanuelle Comets [aut, cre]
, Karl Brendel [ctb],
Thi Huyen Tram Nguyen [ctb], Marc Cerou [ctb], Romain Leroux
[ctb], France Mentre [ctb] |
| Maintainer: | Emmanuelle Comets <[email protected]> |
| License: | GPL (>= 2) |
| Version: | 3.5 |
| Built: | 2024-11-13 04:59:03 UTC |
| Source: | https://github.com/cran/npde |
Routines to compute normalised prediction distribution errors, a metric designed to evaluate non-linear mixed effect models such as those used in pharmacokinetics and pharmacodynamics
Emmanuelle Comets, Karl Brendel, Thi Huyen Tram Nguyen, France Mentre
Maintainer: Emmanuelle Comets <[email protected]>
K. Brendel, E. Comets, C. Laffont, C. Laveille, and F. Mentre. Metrics for external model evaluation with an application to the population pharmacokinetics of gliclazide. Pharmaceutical Research, 23:2036–49, 2006.
PDF documentation for npde 3.0: https://github.com/ecomets/npde30/blob/main/userguide_npde_3.0.pdf
data(theopp) data(simtheopp) # Calling autonpde with dataframes x<-autonpde(theopp,simtheopp,ix="Time",iy="Conc",iid="ID",boolsave=FALSE) print(x)data(theopp) data(simtheopp) # Calling autonpde with dataframes x<-autonpde(theopp,simtheopp,ix="Time",iy="Conc",iid="ID",boolsave=FALSE) print(x)
Access slots of a NpdeData using the object["slot"] format
## S4 method for signature 'NpdeSimData' x[i, j, drop] ## S4 method for signature 'NpdeData' x[i, j, drop] ## S4 replacement method for signature 'NpdeData' x[i, j] <- value ## S4 method for signature 'NpdeRes' x[i, j, drop] ## S4 method for signature 'NpdeObject' x[i, j, drop]## S4 method for signature 'NpdeSimData' x[i, j, drop] ## S4 method for signature 'NpdeData' x[i, j, drop] ## S4 replacement method for signature 'NpdeData' x[i, j] <- value ## S4 method for signature 'NpdeRes' x[i, j, drop] ## S4 method for signature 'NpdeObject' x[i, j, drop]
x |
object from which to extract element(s) or in which to replace element(s) |
i, j
|
indices specifying elements to extract or replace. Indices are numeric or character vectors or empty (missing) or NULL |
drop |
For matrices and arrays. If TRUE the result is coerced to the lowest possible dimension (see the examples). This only works for extracting elements, not for the replacement. See drop for further details |
value |
typically an array-like R object of a similar class as x |
These functions compute normalised prediction distribution errors (npde) and
prediction discrepancies (pd). npde asks the user the name
and structure of the files containing the data, using pdemenu, while
autonpde takes these variables and others as arguments.
autonpde(namobs, namsim, iid, ix, iy, imdv = 0, icens = 0, icov = 0, iipred = 0, boolsave = TRUE, namsav = "output", type.graph = "eps", verbose = FALSE, calc.npde=TRUE, calc.npd=TRUE, decorr.method = "cholesky", cens.method = "cdf", units = list(x="",y=""), detect=FALSE, ties=TRUE, header=TRUE) npde() npde()autonpde(namobs, namsim, iid, ix, iy, imdv = 0, icens = 0, icov = 0, iipred = 0, boolsave = TRUE, namsav = "output", type.graph = "eps", verbose = FALSE, calc.npde=TRUE, calc.npd=TRUE, decorr.method = "cholesky", cens.method = "cdf", units = list(x="",y=""), detect=FALSE, ties=TRUE, header=TRUE) npde() npde()
namobs |
name of the file containing the observed data, or a dataframe
containing the observed data (in both cases, the column containing the
various data required for the computation of the pde can be set using the
arguments |
namsim |
name of the file containing the simulated data, or a dataframe containing the simulated data (the program will assume that subject ID are in column 1 and simulated Y in column 3, see User Guide) |
iid |
name/number of the column in the observed data containing the patient ID; if missing, the program will attempt to detect a column named id |
ix |
name/number of the column in the observed data containing the independent variable (X); ; if missing, the program will attempt to detect a column named X |
iy |
name/number of the column in the observed data containing the dependent variable (Y); if missing, the program will attempt to detect a column with the response |
imdv |
name/number of the column containing information about missing data (MDV), defaults to 0 (column not present) |
icens |
name/number of the column containing information about censored data (cens), defaults to 0 (column not present) |
icov |
name/number of the column(s) containing covariate information defaults to 0 (no covariates) |
iipred |
name/number of the column(s) with individual predictions (ipred), defaults to 0 (individual predictions not available) |
boolsave |
a boolean (TRUE if graphs and results are to be saved to a file, FALSE otherwise), defaults to TRUE |
namsav |
name of the files to which results are to be saved (defaults to "output", which will produce a file called output.eps (if the default format of postscript is kept, see type.graph) for the graphs and a file called output.npde for the numerical results (see value) |
type.graph |
type of graph (one of "eps","jpeg","png","pdf"), defaults to postscript ("eps") |
verbose |
a boolean (TRUE if messages are to be printed as each subject is processed, FALSE otherwise), defaults to FALSE |
calc.npde |
a boolean (TRUE if npde are to be computed, FALSE otherwise), defaults to TRUE |
calc.npd |
a boolean (TRUE if npd are to be computed, FALSE otherwise), defaults to TRUE |
decorr.method |
a character string indicating the method used to decorrelate
observed and simulated data in the computation of npde (see |
cens.method |
a character string indicating the method used to handle
censored data (see |
units |
a list with components x, y and cov (optional), specifying the units respectively for the predictor (x), the response (y), and the covariates (a vector of length equal to the number of covariates). Units will default to (-) if not given. |
detect |
a boolean controlling whether automatic recognition of columns in the dataset is on, defaults to FALSE |
ties |
a boolean (if FALSE, the distributions of pd and npde are smoothed by jittering the values so that there are no ties), defaults to TRUE |
header |
a boolean (TRUE if input files have headers, FALSE otherwise), defaults to TRUE |
Both functions compute the normalised prediction distribution errors (and/or
prediction discrepancies) in the same way. npde is an interactive
function whereas autonpde takes all required input as arguments.
Diagnostic graphs are produced for npd, and npde are used in the tests as their distribution takes into account the correlation between repeated observations.
When the computation of npde fails because of numerical problems, error messages are printed out, then pd are computed instead and graphs of pd are plotted so that the user may evaluate why the computation failed.
The function also prints out the characteristics of the distribution of the npde (mean, variance, skewness and kurtosis) as well as the results of the statistical tests applied to npde. In addition, if boolsave is TRUE, two files are created:
the numerical results are saved in a file with extension .npde (the name of which is given by the user). The file contains the components id, xobs, ypred, npde, pd stored in columns
the graphs are saved to a file with the same name as the results file, and with extension depending on the format.
An object of class NpdeObject
Emmanuelle Comets <[email protected]>
K. Brendel, E. Comets, C. Laffont, C. Laveille, and F. Mentre. Metrics for external model evaluation with an application to the population pharmacokinetics of gliclazide. Pharmaceutical Research, 23:2036–49, 2006.
PDF documentation for npde 3.0: https://github.com/ecomets/npde30/blob/main/userguide_npde_3.0.pdf
data(theopp) data(simtheopp) # Calling autonpde with dataframes x<-autonpde(theopp,simtheopp,1,3,4,boolsave=FALSE) x head(x["results"]["res"]) plot(x)data(theopp) data(simtheopp) # Calling autonpde with dataframes x<-autonpde(theopp,simtheopp,1,3,4,boolsave=FALSE) x head(x["results"]["res"]) plot(x)
This function is used to build the distribution of pd/npde using the simulations under the model. The default is to build only the distribution of pd, and to sample from N(0,1) when building the distribution of npde under the null hypothesis.
dist.pred.sim(npdeObject,nsamp, ...)dist.pred.sim(npdeObject,nsamp, ...)
npdeObject |
|
nsamp |
number of datasets (defaults to 100 or to the number of replications if it is smaller) |
... |
additional arguments. Currently only the value of calc.npd and calc.npde may be passed on, and will override their corresponding value in the "options" slot of npdeObject |
an object of class NpdeObject; the ["results"] slot will contain pd and/or npde for a sample of the simulated datasets (depending on whether calc.npd/calc.npde are set), stored in pd.sim and/or npde.sim
Emmanuelle Comets <[email protected]>
K. Brendel, E. Comets, C. Laffont, C. Laveille, and F. Mentre. Metrics for external model evaluation with an application to the population pharmacokinetics of gliclazide. Pharmaceutical Research, 23:2036–49, 2006.
data(theopp) data(simtheopp) x<-autonpde(theopp,simtheopp,1,3,4,boolsave=FALSE) # Use random samples from N(0,1) to obtain a prediction interval on the empirical cdf of the npde plot(x,plot.type="ecdf",bands=TRUE,approx.pi=TRUE) # defaults to computing the pd and npde for 100 simulated datasets # (in the theophylline example, this uses all the simulated datasets) x<-dist.pred.sim(x) # Use the npde from the simulated datasets to obtain a prediction interval on the empirical cdf plot(x,plot.type="ecdf",bands=TRUE,approx.pi=FALSE)data(theopp) data(simtheopp) x<-autonpde(theopp,simtheopp,1,3,4,boolsave=FALSE) # Use random samples from N(0,1) to obtain a prediction interval on the empirical cdf of the npde plot(x,plot.type="ecdf",bands=TRUE,approx.pi=TRUE) # defaults to computing the pd and npde for 100 simulated datasets # (in the theophylline example, this uses all the simulated datasets) x<-dist.pred.sim(x) # Use the npde from the simulated datasets to obtain a prediction interval on the empirical cdf plot(x,plot.type="ecdf",bands=TRUE,approx.pi=FALSE)
Performs test on the selected variable (which=one of npde, pd or npd) or on a numeric vector
gof.test(object, parametric = TRUE, ...) printgoftest(object, ...)gof.test(object, parametric = TRUE, ...) printgoftest(object, ...)
object |
an object (currently has methods for types numeric, NpdeRes and NpdeObject) |
parametric |
a boolean. If TRUE (default), parametric tests are performed |
... |
additional arguments passed on to the function; special arguments are |
If object is an NpdeObject and an argument covsplit=TRUE is given in ..., in addition to the global descriptive statistics and tests, tests will be performed for each covariate in which.cov. This argument can be set in ...; barring an explicit specification, the component which.cov of the prefs slot for a NpdeObject object will be used. The default value is which.cov="all", which produces tests for each covariate in the dataset. Two additional dataframes will then be present:
descriptive statistics and test p-values split by covariate and by categories
p-values split by covariate; for each covariate, two tests are performed: the first test is a correlation test for continuous covariates and a Chi-square test for categorical covariates; the second test is defined using the p-values of the global tests split by each category, and appling a Bonferroni correction to obtain an overall p-value (see PDF documentation for details)
The p.value elements is a named vector with four components:
p-value for the mean test (Wilcoxon test if parametric=FALSE, Student test if parametric=TRUE)
p-value for the variance test (parametric=FALSE, Fisher test if parametric=TRUE)
p-value for the distribution test (Shapiro-test for normality (npd, npde)/Kolmogorove-Smirnov test for uniformity)
p-value for the global test (combination of the mean, variance and distribution tests with a Bonferroni correction)
The p-values are adjusted using a Bonferroni correction: the raw p-values of the 3 individual tests are multiplied by 3, and the p-value for the global test is equal to the minimum of the adjusted p-values.
A list with the following elements:
mean
standard error of the mean
variance
standard error on variance
kurtosis (see kurtosis)
skewness (see skewness)
p-values for several tests (see below)
K. Brendel, E. Comets, C. Laffont, C. Laveille, and F. Mentre. Metrics for external model evaluation with an application to the population pharmacokinetics of gliclazide. Pharmaceutical Research, 23:2036–49, 2006.
K. Brendel, E. Comets, C. Laffont, and F. Mentre. Evaluation of different tests based on observations for external model evaluation of population analyses. Journal of Pharmacokinetics and Pharmacodynamics, 37:49–65, 2010.
data(theopp) data(simtheopp) #' # Calling autonpde with dataframes x<-autonpde(theopp,simtheopp,1,3,4,boolsave=FALSE) gof.test(x)data(theopp) data(simtheopp) #' # Calling autonpde with dataframes x<-autonpde(theopp,simtheopp,1,3,4,boolsave=FALSE) gof.test(x)
Computes the kurtosis.
kurtosis(x)kurtosis(x)
x |
a numeric vector containing the values whose kurtosis is to be computed. NA values are removed in the computation. |
If , then the kurtosis of
is defined as:
The kurtosis of x.
G. Snedecor, W. Cochran. Statistical Methods, Wiley-Blackwell, 1989
x <- rnorm(100) kurtosis(x)x <- rnorm(100) kurtosis(x)
Functions used by plot functions to define the boundaries of the bins on the X-axis
npde.binning(xvec, plot.opt, verbose = FALSE)npde.binning(xvec, plot.opt, verbose = FALSE)
xvec |
a vector of values for the X-axis of the plot |
plot.opt |
graphical options |
verbose |
boolean (defaults to FALSE). If TRUE, a table showing how the binning was performed |
These functions are normally not called by the end-user but are now exported for use in the saemix package.
a list with 3 elements, xgrp (the number of the bin associated with each element of xvec), xcent (a named vector containing the mean of the elements of xvec contained in each bin; the name of the bin is the interval), and xgroup (a vector with the group associated to each element of xvec after binning) If verbose is TRUE, a table showing the bins is shown, giving the interval of xvec associated with each bin, the mean value of xvec in each bin, and the number of observations
Emmanuelle Comets <[email protected]>
K. Brendel, E. Comets, C. Laffont, C. Laveille, and F. Mentre. Metrics for external model evaluation with an application to the population pharmacokinetics of gliclazide. Pharmaceutical Research, 23:2036–49, 2006.
Specifies the method used to handle censored data (data below the limit of quantification LOQ
Several methods are available to handle censored data.
pd and npde for censored data will be set to NA
for an observation ycens_ij under the LOQ, a pd_ij will be imputed in the uniform distribution [0-pLOQ_ij] where pLOQ_ij is the probability that y_ij is below LOQ, according to the model; the predictive distribution will then be used to obtain a corresponding y*_ij. This is also performed for all simulated data, and the npde are then computed on the completed dataset containing the observed y_ij for the uncensored data and the y*_ij imputed for the censored data. This method is the default.
an observation ycens_ij is replaced by the individual prediction according to the model (ipred, which must be present in the dataset). Simulated data are left untouched.
an observation ycens_ij is replaced by the population prediction according to the model. Simulated data are left untouched.
an observation ycens_ij is replaced by the value of the LOQ. Simulated data are left untouched.
This is not a function and does not have a return value, this is a statistical method.
More details can be found in the PDF documentation.
K. Brendel, E. Comets, C. Laffont, C. Laveille, and F. Mentre. Metrics for external model evaluation with an application to the population pharmacokinetics of gliclazide. Pharmaceutical Research, 23:2036–49, 2006.
## Not run: # You need to have gridExtra installed to successfully run this example if(requireNamespace("gridExtra", quietly=TRUE)) { data(warfarin) data(simwarfarinCov) wcov<-autonpde(namobs=warfarin,namsim=simwarfarinCov, iid=1,ix=2,iy=4,icov=c(3,6:8), namsav="warfCov", units=list(x="hr",y="mg/L", covariates=c("mg","kg","-","yr"))) # Diagnostic plots for warfarin with a covariate model plot(wcov) # Covariate plots xwt.scatt<-plot(wcov, plot.type="x.scatter", covsplit=TRUE, which.cov="wt") xwt.qqplot<-plot(wcov, plot.type="qqplot", covsplit=TRUE, which.cov="wt") xwt.box<-plot(wcov, plot.type="covariates", which.cov="wt") xsex.scatt<-plot(wcov, plot.type="x.scatter", covsplit=TRUE, which.cov="sex") xsex.qqplot<-plot(wcov, plot.type="qqplot", covsplit=TRUE, which.cov="sex") xsex.box<-plot(wcov, plot.type="covariates", which.cov="sex") # Transforming the reference profile for npd, compared to a VPC plot plot.tnpd<-plot(wcov, plot.type="x.scatter", ref.prof=list(id=2), main="tnpd with reference profile ID=2") plot.vpc<-plot(wcov, plot.type="vpc", main="VPC") gridExtra::grid.arrange(grobs=list(plot.tnpd, plot.vpc), nrow=1, ncol=2) } ## End(Not run)## Not run: # You need to have gridExtra installed to successfully run this example if(requireNamespace("gridExtra", quietly=TRUE)) { data(warfarin) data(simwarfarinCov) wcov<-autonpde(namobs=warfarin,namsim=simwarfarinCov, iid=1,ix=2,iy=4,icov=c(3,6:8), namsav="warfCov", units=list(x="hr",y="mg/L", covariates=c("mg","kg","-","yr"))) # Diagnostic plots for warfarin with a covariate model plot(wcov) # Covariate plots xwt.scatt<-plot(wcov, plot.type="x.scatter", covsplit=TRUE, which.cov="wt") xwt.qqplot<-plot(wcov, plot.type="qqplot", covsplit=TRUE, which.cov="wt") xwt.box<-plot(wcov, plot.type="covariates", which.cov="wt") xsex.scatt<-plot(wcov, plot.type="x.scatter", covsplit=TRUE, which.cov="sex") xsex.qqplot<-plot(wcov, plot.type="qqplot", covsplit=TRUE, which.cov="sex") xsex.box<-plot(wcov, plot.type="covariates", which.cov="sex") # Transforming the reference profile for npd, compared to a VPC plot plot.tnpd<-plot(wcov, plot.type="x.scatter", ref.prof=list(id=2), main="tnpd with reference profile ID=2") plot.vpc<-plot(wcov, plot.type="vpc", main="VPC") gridExtra::grid.arrange(grobs=list(plot.tnpd, plot.vpc), nrow=1, ncol=2) } ## End(Not run)
Specifies the method used to decorrelate observed and simulated data
x |
a square matrix
@return This is not a function and does not have a return value, this is a statistical method. |
More details can be found in the PDF documentation.
K. Brendel, E. Comets, C. Laffont, C. Laveille, and F. Mentre. Metrics for external model evaluation with an application to the population pharmacokinetics of gliclazide. Pharmaceutical Research, 23:2036–49, 2006.
Save the graphs to a file on disk
npde.graphs(object, ...)npde.graphs(object, ...)
object |
a NpdeObject object |
... |
optional arguments to replace options in object |
The following options can be changed by passing the appropriate arguments: namsav (string giving the root name of the files, an extension depending on the type of graph will be added), namgr (string giving the full name of the file), type.graph (one of "eps", "pdf", "jpeg", "png")
No return value, called for side effects
K. Brendel, E. Comets, C. Laffont, C. Laveille, and F.Mentre. Metrics for external model evaluation with an application to the population pharmacokinetics of gliclazide. Pharmaceutical Research, 23:2036–49, 2006.
Boxplot of the selected variable versus categories of covariates
npde.plot.covariate(npdeObject, which.y="npd", ...)npde.plot.covariate(npdeObject, which.y="npd", ...)
npdeObject |
|
which.y |
a string specifying the variable on the Y-axis (one of "yobs", "npde", "pd", "npd") |
... |
additional arguments to be passed on to the function, to control which metric (npde, pd, npd) is used or to override graphical parameters (see the PDF document for details, as well as |
For a categorical covariate, boxplots are produced for each category. Continous covariates are split into quantile (by default, first quartile (<Q1), interquartile range (Q1-Q3) and upper quartile (>Q3), but the number of categories can be set by using the ncat argument).
For each category, the median according to simulations under the model is shown (it can be suppressed by using the argument bands=FALSE)..
a ggplot object or a list of ggplot objects (grobs)
Emmanuelle Comets <[email protected]>
K. Brendel, E. Comets, C. Laffont, F. Mentre F. Evaluation of different tests based on observations for external model evaluation of population analyses. Journal of Pharmacokinetics and Pharmacodynamics, 37:49-65, 2010.
npde, autonpde, set.plotoptions, npdeControl
Produces a spaghetti plot of the data
npde.plot.data(npdeObject, ...)npde.plot.data(npdeObject, ...)
npdeObject |
|
... |
additional arguments to be passed on to the function, to control which metric (npde, pd, npd) is used or to override graphical parameters (see the PDF document for details, as well as |
a ggplot object or a list of ggplot objects (grobs)
The default diagnostic plots produced after a call to npde or autonpde include a histogram of the distribution, a QQ-plot compared to the theoretical distribution, and scatterplots versus the independent variable and versus the population predictions from the model
npde.plot.default(npdeObject, ...)npde.plot.default(npdeObject, ...)
npdeObject |
|
... |
additional arguments to be passed on to the function, to control which metric (npde, pd, npd) is used or to override graphical parameters (see the PDF document for details, as well as |
By default, npd are used for the diagnostic plots. If an unknown argument to which (eg which="XXX") is given, this is changed to npd (with a warning message if verbose=TRUE or the verbose option in the option slot of the npdeObject is TRUE).
a ggplot object or a list of ggplot objects (grobs)
Produces a plot of the cdistribution of a metric compared to their theoretical distribution. Three types of distribution plots are available: a histogram, a QQ-plot, or the empirical cdf.
npde.plot.dist(npdeObject, which="npd", dist.type="qqplot", ...)npde.plot.dist(npdeObject, which="npd", dist.type="qqplot", ...)
npdeObject |
|
which |
a string determining which metric to plot (one of "npde", "pd" or "npd"), defaults to "npd" |
dist.type |
string, one of "ecdf" (empirical cumulative density function), "hist" (histogram) or "qqplot" (QQ-plot of the empirical distribution versus the theoretical quantiles) to determine which type of plot (default is "qqplot") |
... |
additional arguments to be passed on to the function, to control which metric (npde, pd, npd) is used or to override graphical parameters (see the PDF document for details, as well as |
a ggplot object or a list of ggplot objects (grobs)
Emmanuelle Comets <[email protected]>
K. Brendel, E. Comets, C. Laffont, C. Laveille, and F. Mentre. Metrics for external model evaluation with an application to the population pharmacokinetics of gliclazide. Pharmaceutical Research, 23:2036–49, 2006.
npde, autonpde, set.plotoptions
Plots the probability that the observations are below the LOQ along with the model predicted interval
npde.plot.loq(npdeObject,xaxis="x",nsim=200,...)npde.plot.loq(npdeObject,xaxis="x",nsim=200,...)
npdeObject |
|
xaxis |
a string character, one of "x" (to plot P(Y<LOQ) versus the value of the independent predictor) or "ypred" (versus the value of the population predictions). Defaults to "x" |
nsim |
number of simulations to be used for the computation of the prediction interval |
... |
additional arguments to be passed on to the function, to control which metric (npde, pd, npd) is used or to override graphical parameters (see the PDF document for details, as well as |
a ggplot object or a list of ggplot objects (grobs)
Emmanuelle Comets <[email protected]>
K. Brendel, E. Comets, C. Laffont, C. Laveille, and F. Mentre. Metrics for external model evaluation with an application to the population pharmacokinetics of gliclazide. Pharmaceutical Research, 23:2036–49, 2006.
npde, autonpde, set.plotoptions
Plots for pd and npde
npde.plot.pd(npdeObject, ...) npde.plot.npde(npdeObject, ...) npde.plot.npd(npdeObject, ...)npde.plot.pd(npdeObject, ...) npde.plot.npde(npdeObject, ...) npde.plot.npd(npdeObject, ...)
npdeObject |
|
... |
additional arguments to be passed on to the function, to control which metric (npde, pd, npd) is used or to override graphical parameters (see the PDF document for details, as well as |
a ggplot object or a list of ggplot objects (grobs)
Produces a scatterplot. Different types of scatterplots can be produced, with associated prediction bands (see details).
npde.plot.scatterplot(npdeObject, which.x="x", which.y="npd", ref.prof=NULL, ...)npde.plot.scatterplot(npdeObject, which.x="x", which.y="npd", ref.prof=NULL, ...)
npdeObject |
|
which.x |
a string specifying the variable on the X-axis (one of "x", "pred", "cov") |
which.y |
a string specifying the variable on the Y-axis (one of "yobs", "npde", "pd", "npd"), defaults to "npd" |
ref.prof |
either a character string (one of "covariate" or "all"), or a named list specifying the characteristics of the reference profile (see details) |
... |
additional arguments to be passed on to the function, to control which metric (npde, pd, npd) is used or to override graphical parameters (see the PDF document for details, as well as |
VPC: obtained using which.x="x", which.y="yobs"
Scatterplots of npde/pd/npd can be obtained versus "x" (independent variable) or "pred" (population predictions from the model)
Scatterplots of npde/pd/npd/observations can be obtained versus covariates by setting the which.x argument to "cov" and selecting the appropriate which.y. The function will use the covariates in the which.cov element of the prefs slot. This can be overriden to cycle over all the covariates in the dataset by supplying the argument which.cov="all" in the call to the function.
Reference profile: a reference profile can be added to scatterplots of npd and npde versus the independent variable (see Comets et al. 2013)
If ref.prof="all" (and covsplit is FALSE), the reference plot will be computed over all subjects using the mean and SD of all simulated data in each bin (see documentation).
If ref.prof="covariate" and an additional argument covsplit is given (covsplit=TRUE), the reference plot will be adjusted for each covariate category over all the covariates in the which.cov element of the prefs slot (see npdeControl for details on the prefs slot of the npdeObject).
If ref.prof is given as a named list (eg list(ID=c(1,5)) or list(sex=0, dose=c(50,100)), where names should refer to columns in the data file (eg ID should be a column in the data)), the reference profile will be obtained by combining (in the first example above, the reference profile will be obtained using the simulated data for subjects 1 and 5, while in the second example it will be computed using the subjects with sex=0 given doses 50 or 100).
a ggplot object or a list of ggplot objects (grobs)
Emmanuelle Comets <[email protected]>
K. Brendel, E. Comets, C. Laffont, C. Laveille, and F. Mentre. Metrics for external model evaluation with an application to the population pharmacokinetics of gliclazide. Pharmaceutical Research, 23:2036–49, 2006.
E. Comets, T.H.T. Nguyen, and F. Mentré F. Additional features and graphs in the new npde library for R. 22th meeting of the Population Approach Group in Europe, Glasgow, United Kingdom, 2013.
npde, autonpde, set.plotoptions, npdeControl
Select plot for a NpdeObject object
npde.plot.select(npdeObject,data=FALSE,ecdf=FALSE,qqplot=FALSE, histogram=FALSE, x.scatter=FALSE,pred.scatter=FALSE,x.box=FALSE,pred.box=FALSE, cov.scatter=FALSE, cov.x.scatter=FALSE, cov.pred.scatter=FALSE,cov.x.box=FALSE,cov.pred.box=FALSE, cov.ecdf=FALSE, cov.hist=FALSE, cov.qqplot=FALSE, vpc=FALSE,...)npde.plot.select(npdeObject,data=FALSE,ecdf=FALSE,qqplot=FALSE, histogram=FALSE, x.scatter=FALSE,pred.scatter=FALSE,x.box=FALSE,pred.box=FALSE, cov.scatter=FALSE, cov.x.scatter=FALSE, cov.pred.scatter=FALSE,cov.x.box=FALSE,cov.pred.box=FALSE, cov.ecdf=FALSE, cov.hist=FALSE, cov.qqplot=FALSE, vpc=FALSE,...)
npdeObject |
|
data |
boolean, whether to produce a plot of the data |
ecdf |
boolean, whether to produce a distribution plot of the empirical distribution function |
qqplot |
boolean, whether to produce a QQ-plot of the empirical distribution function |
histogram |
boolean, whether to produce a histogram of the metric |
x.scatter |
boolean, whether to produce a scatterplot of the metric as a function of X |
pred.scatter |
boolean, whether to produce a scatterplot of the metric as a function of predictions |
x.box |
boolean, whether to produce whisker plots of the metric as a function of X |
pred.box |
boolean, whether to produce whisker plots of the metric as a function of predictions |
cov.scatter |
boolean, whether to produce a scatterplot of the metric as a function of covariate(s) |
cov.x.scatter |
boolean, whether to produce a scatterplot of the metric as a function of X, split by covariate(s) |
cov.pred.scatter |
boolean, whether to produce a scatterplot of the metric as a function of predictions, split by covariate(s) |
cov.x.box |
boolean, whether to produce whisker plots of the metric as a function of X, split by covariate(s) |
cov.pred.box |
boolean, whether to produce whisker plots of the metric as a function of predictions, split by covariate(s) |
cov.ecdf |
boolean, whether to produce a distribution plot of the empirical distribution function, split by covariate(s) |
cov.hist |
boolean, whether to produce a distribution plot of the empirical distribution function, split by covariate(s) |
cov.qqplot |
boolean, whether to produce a distribution plot of the empirical distribution function, split by covariate(s) |
vpc |
boolean, whether to produce a VPC |
... |
additional arguments to be passed on to the function, to control which metric (npde, pd, npd) is used or to override graphical parameters (see the PDF document for details, as well as |
a ggplot object or a list of ggplot objects (grobs)
Emmanuelle Comets <[email protected]>
K. Brendel, E. Comets, C. Laffont, C. Laveille, and F. Mentre. Metrics for external model evaluation with an application to the population pharmacokinetics of gliclazide. Pharmaceutical Research, 23:2036–49, 2006.
npde, autonpde, set.plotoptions
Plots split by covariate for a NpdeObject object (equivalent to using covsplit=TRUE with the appropriate plot.type)
npde.plot.splitcov(npdeObject, which.plot="x", ...)npde.plot.splitcov(npdeObject, which.plot="x", ...)
npdeObject |
|
which.plot |
one of "x" (scatterplots of the metric versus X), "pred" (scatterplots of the metric versus predictions), "ecdf" (empirical distribution function), "hist" (histogram), "qqplot" |
... |
additional arguments to be passed on to the function, to control which metric (npde, pd, npd) is used or to override graphical parameters (see the PDF document for details, as well as |
a ggplot object or a list of ggplot objects (grobs)
Save the results to a table on disk
npde.save(object, ...)npde.save(object, ...)
object |
a NpdeObject object |
... |
optional arguments to replace options in object |
The following options can be changed by passing the appropriate arguments: namsav (string giving the root name of the files, an extension .npde will be added), nameres (string giving the full name of the file)
No return value, called for side effects
K. Brendel, E. Comets, C. Laffont, C. Laveille, and F.Mentre. Metrics for external model evaluation with an application to the population pharmacokinetics of gliclazide. Pharmaceutical Research, 23:2036–49, 2006.
Set, replace and check options for an NpdeObject
npdeControl(boolsave = TRUE, namsav = "output", type.graph = "eps", verbose = FALSE, calc.npde = TRUE, calc.npd = TRUE, decorr.method = "cholesky", cens.method = "omit", ties = TRUE, sample = FALSE) check.control.options(opt) replace.control.options(opt,...) replace.control.options(opt, ...) check.control.options(opt)npdeControl(boolsave = TRUE, namsav = "output", type.graph = "eps", verbose = FALSE, calc.npde = TRUE, calc.npd = TRUE, decorr.method = "cholesky", cens.method = "omit", ties = TRUE, sample = FALSE) check.control.options(opt) replace.control.options(opt,...) replace.control.options(opt, ...) check.control.options(opt)
boolsave |
whether to save the results (a file containing the numerical results and a file with the graphs) |
namsav |
the root name of the files to save to (the file with the results will be named ROOTNAME.npde and the graphs will be saved to ROOTNAME.format where format is given by the type.graph argument) |
type.graph |
type of graph to save to (one of "eps", "pdf", "jpeg", "png") |
verbose |
a boolean; if TRUE, a message is printed as the computation of the npde begins for each new subject |
calc.npde |
a boolean; TRUE to compute npde |
calc.npd |
a boolean; TRUE to compute npd |
decorr.method |
the method used to decorrelate simulated and observed data (see |
cens.method |
the method used to handle censored data (see |
ties |
if FALSE, a smoothing will be applied to prediction discrepancies to avoid ties |
sample |
if TRUE, the test on the pd will be performed after randomly sampling only pd per subject |
opt |
a list of control options to be checked |
... |
named parameters to be changed. The names will be compared to the names of the control variables and changed, with warnings issued for names that do not match. |
A list of settings for the computation of pd/npde
This function is used to create a NpdeData object, representing a longitudinal data structure, and fill it with data from a dataframe or a file on disk
npdeData(name.data,header=TRUE,sep="",na.strings=c(".","NA"),name.group, name.predictor, name.response, name.covariates,name.cens,name.miss,name.ipred, units=list(x="",y="",covariates=c()), detect=TRUE,verbose=FALSE)npdeData(name.data,header=TRUE,sep="",na.strings=c(".","NA"),name.group, name.predictor, name.response, name.covariates,name.cens,name.miss,name.ipred, units=list(x="",y="",covariates=c()), detect=TRUE,verbose=FALSE)
name.data |
name of the file containing the observed data, or a dataframe containing the observed data |
header |
boolean indicating whether the file has a header (a header is mandatory if detect is TRUE) |
sep |
field separator (for files on disk) |
na.strings |
strings to be considered as indicating NA |
name.group |
name/number of the column in the observed data containing the patient ID (if missing and detect is TRUE, columns named id, subject or sujet (regardless of case) will be assumed to contain this information) |
name.predictor |
name/number of the column in the observed data containing the independent variable X (if missing and detect is TRUE, columns named xobs, time, dose, x, temps, tim (regardless of case) will be assumed to contain this information) |
name.response |
name/number of the column in the observed data containing the dependent variable Y (if missing and detect is TRUE, columns named yobs, response, resp, conc, concentration (regardless of case) will be assumed to contain this information) |
name.covariates |
name/number of the column(s) containing covariate information (optional) |
name.cens |
name/number of the column containing information about censored data (cens) (if missing and detect is TRUE, column with a name containing cens (regardless of case) will be assumed to contain this information) |
name.miss |
name/number of the column containing information about missing data (MDV) (if missing and detect is TRUE, column called mdv or miss (regardless of case) will be assumed to contain this information) |
name.ipred |
name/number of the column(s) with individual predictions (ipred) (if missing and detect is TRUE, column with a name containing ipred (regardless of case) will be assumed to contain this information) |
units |
a list with components x, y and cov (optional), specifying the units respectively for the predictor (x), the response (y), and the covariates (a vector of length equal to the number of covariates). Units will default to (-) if not given. |
detect |
a boolean controlling whether automatic recognition of columns in the dataset is on, defaults to TRUE |
verbose |
whether to print warning messages, defaults to FALSE (set to TRUE to check how data is being handled) |
an object of class NpdeData
Emmanuelle Comets <[email protected]>
K. Brendel, E. Comets, C. Laffont, C. Laveille, and F. Mentré. Metrics for external model evaluation with an application to the population pharmacokinetics of gliclazide. Pharmaceutical Research, 23:2036–49, 2006.
data(theopp) x<-npdeData(theopp) # Automatic detection print(x) x<-npdeData(theopp,name.group="ID",name.predictor="Time",name.response="Conc", name.covariates=c("Wt"),units=list(x="hr",y="mg/L",covariates="kg")) # Explicit print(x)data(theopp) x<-npdeData(theopp) # Automatic detection print(x) x<-npdeData(theopp,name.group="ID",name.predictor="Time",name.response="Conc", name.covariates=c("Wt"),units=list(x="hr",y="mg/L",covariates="kg")) # Explicit print(x)
A longitudinal data structure
NpdeData objects are typically created by a call to npdeData contain the following slots:
character string giving the name of the grouping term (ID)
character string giving the name of the predictor (X)
character string giving the name of the response (Y)
character string giving the name of the censoring indicator in the original dataset (renamed to cens)
character string giving the name of the missing data indicator in the original dataset (renamed to mdv)
vector of character string giving the name(s) of the covariates
character string giving the name of the individual predictions
(optional) a list with the units for X, Y, and covariates
a dataframe containing the data
number of subjects
total number of non-missing observations
vector of size N giving the number of non-missing observations for each subject
index of non-missing observations
index of censored observations (non-missing)
a vector of boolean indicating for each observation whether it is missing (FALSE) or available (TRUE)
the censoring value
Prints a short summary of object npde.data
QQ-plot for NpdeData object (TODO: change for NpdeObject in final package)
methods(class="NpdeData") showClass("NpdeData")methods(class="NpdeData") showClass("NpdeData")
An object of class NpdeObject
NpdeObject objects are typically created by calls to npde or autonpde. They contain the following slots:
an object of class NpdeData, containing the observed data
an object of class NpdeSimData, containing the simulated data
an object of class NpdeRes, containing the results
a list of options
a list of graphical preferences for the plots
Prints a summary of object
Prints a short summary of object
Prints a detailed summary of object
Diagnostic and other plots. More details can be found in plot.NpdeObject
Returns a summary of object x in list format
Returns goodness-of-fit tests
Sets options for graphs (internal method used in plots)
npde, autonpde, NpdeData, NpdeSimData, NpdeRes, gof.test
methods(class="NpdeObject") showClass("NpdeObject")methods(class="NpdeObject") showClass("NpdeObject")
This function is used to create a NpdeSimData object containing the simulated data corresponding to an NpdeData object
npdeSimData(npde.data, name.simdata, header=TRUE, sep="", na.strings=c("NA","."), detect=FALSE, verbose=FALSE)npdeSimData(npde.data, name.simdata, header=TRUE, sep="", na.strings=c("NA","."), detect=FALSE, verbose=FALSE)
npde.data |
a NpdeData object |
name.simdata |
name of the file containing the simulated data, or a dataframe containing it |
header |
boolean indicating whether the file has a header (a header is mandatory if detect is TRUE) |
sep |
field separator (for files on disk) |
na.strings |
strings to be considered as indicating NA |
detect |
a boolean controlling whether automatic recognition of columns in the dataset is on, defaults to FALSE if FALSE, the first 3 columns of the simulated data file will will be used as simulated id, predictor and response respectively if TRUE, the function will look for columns named respectively idsim, xsim and ysim (it will fail with an error message if these columns are not present in the simulated data) |
verbose |
whether to print warning messages, defaults to FALSE (set to TRUE to check how data is being handled) |
an object of class NpdeSimData
Emmanuelle Comets <[email protected]>
A longitudinal data structure, with simulated data
NpdeSimData objects are created by associating an NpdeData object with matching simulated data, and they contain the following slots.
number of replications)
a dataframe containing the simulated data, with columns: idsim (subject id), irsim (replication index), xsim (simulated x), ysim (simulated response). After a call to npde or autonpde, an additional column ydsim (decorrelated replicated data) will be added.
Prints a summary of object npde.simdata
Prints a short summary of object npde.simdata
Prints a detailed summary of object npde.simdata
showClass("NpdeSimData")showClass("NpdeSimData")
Plots the data in a NpdeData object
## S3 method for class 'NpdeData' plot(x, y, ...)## S3 method for class 'NpdeData' plot(x, y, ...)
x |
a NpdeData object |
y |
unused, here for compatibility with the base plot function |
... |
additional graphical parameters to be passed on to the plot |
The default plot is a spaghetti plot of all the data, with a line joining the observations for each subject. If censored data is present, it is shown with a different symbol and colour.
currently does not return anything, use plot(x, plot.type="data") on the npdeObject x (TODO; a ggplot object)
K. Brendel, E. Comets, C. Laffont, C. Laveille, and F.Mentre. Metrics for external model evaluation with an application to the population pharmacokinetics of gliclazide. Pharmaceutical Research, 23:2036–49, 2006.
data(theopp) x<-npdeData(theopp,name.group="ID",name.predictor="Time",name.response="Conc", name.covariates=c("Wt"),units=list(x="hr",y="mg/L",covariates="kg")) plot(x)data(theopp) x<-npdeData(theopp,name.group="ID",name.predictor="Time",name.response="Conc", name.covariates=c("Wt"),units=list(x="hr",y="mg/L",covariates="kg")) plot(x)
Plots the data and diagnostic plots in a NpdeObject object
## S3 method for class 'NpdeObject' plot(x, y, ...)## S3 method for class 'NpdeObject' plot(x, y, ...)
x |
a NpdeObject object |
y |
unused, here for compatibility with the base plot function |
... |
additional graphical parameters, which when given will supersede graphical preferences stored in the object |
The default plots are represented as a 2x2 array with distribution plots on the top row (histogram and QQ-plot), and scatterplots of npde versus independent variable and population predictions on the bottom row. The graph is plotted in a graphic device window, unless the result is stored in an object (eg myplot<-plot(x)) which can then be printed (eg using print(myplot)).
@references K. Brendel, E. Comets, C. Laffont, C. Laveille, and F.Mentre. Metrics for external model evaluation with an application to the population pharmacokinetics of gliclazide. Pharmaceutical Research, 23:2036–49, 2006.
a ggplot object or a list of ggplot objects (grobs)
data(theopp) data(simtheopp) x<-autonpde(theopp,simtheopp,iid="ID",ix="Time", iy="Conc", boolsave=FALSE) plot(x)data(theopp) data(simtheopp) x<-autonpde(theopp,simtheopp,iid="ID",ix="Time", iy="Conc", boolsave=FALSE) plot(x)
prints objects of classes NpdeData, NpdeSimData, NpdeRes and NpdeObject
## S3 method for class 'NpdeData' print(x, nlines = 10, ...) ## S3 method for class 'NpdeRes' print(x, nlines = 10, ...) ## S3 method for class 'NpdeObject' print(x, nlines = 10, ...)## S3 method for class 'NpdeData' print(x, nlines = 10, ...) ## S3 method for class 'NpdeRes' print(x, nlines = 10, ...) ## S3 method for class 'NpdeObject' print(x, nlines = 10, ...)
x |
an object of class NpdeData, NpdeSimData, NpdeRes or NpdeObject |
nlines |
number of lines from the dataset to print |
... |
Additional arguments (ignored) |
None
This function is used to set options for graphs
set.plotoptions(object) ## Default S3 method: set.plotoptions(object) ## S3 method for class 'NpdeData' set.plotoptions(object) ## S3 method for class 'NpdeObject' set.plotoptions(object)set.plotoptions(object) ## Default S3 method: set.plotoptions(object) ## S3 method for class 'NpdeData' set.plotoptions(object) ## S3 method for class 'NpdeObject' set.plotoptions(object)
object |
an object of class NpdeData or NpdeObject |
See documentation for a list of available options.
a list of options for graphs
Emmanuelle Comets <[email protected]>
Prints the structure of objects from the package
## S4 method for signature 'NpdeData' show(object) ## S4 method for signature 'NpdeSimData' show(object) ## S4 method for signature 'NpdeRes' show(object) ## S4 method for signature 'NpdeObject' show(object)## S4 method for signature 'NpdeData' show(object) ## S4 method for signature 'NpdeSimData' show(object) ## S4 method for signature 'NpdeRes' show(object) ## S4 method for signature 'NpdeObject' show(object)
object |
an object from the npde package (NpdeData, NpdeRes, NpdeObject) |
Prints the contents of an object
showall(object) ## S3 method for class 'NpdeRes' showall(object) ## S3 method for class 'NpdeObject' showall(object)showall(object) ## S3 method for class 'NpdeRes' showall(object) ## S3 method for class 'NpdeObject' showall(object)
object |
a NpdeData object |
No return value, shows the object
The simtheopp dataset contains 100 simulations using the design of
dataset theopp. These simulations are used to compute npde.
The control file used to perform the simulations can be found in the
subdirectory 'doc' within the library npde.
simtheoppsimtheopp
A data frame with 132000 rows and 3 variables This data frame contains the following columns:
an ordered factor with levels 1, ..., 12
identifying the subject on whom the observation was made. The ordering is
first by simulation then by increasing time.
time since drug administration when the sample was drawn (hr).
simulated theophylline concentration (mg/L).
See theopp for a description of the original dataset.
The simulated data was obtained using the software NONMEM. A one-compartment model was fit to the data. An exponential interindividual variability was assumed for the three parameters (absorption rate constant ka, volume of distribution V and clearance CL) and a combined additive and proportional residual error model was usd. The estimated parameters were then used to simulate 100 datasets with the same structure as the original dataset. Thus, for each observation in the original dataset, the simulated dataset contains 100 simulations under the model used for the estimation.
This dataset is provided so that users can figure out what type of data is needed for the computation of prediction distribution errors. More information can be found in the User Guide distributed along with this package, which contains a run-through of the theophylline example.
Boeckmann, A. J., Sheiner, L. B. and Beal, S. L. (1994), NONMEM Users Guide: Part V, NONMEM Project Group, University of California, San Francisco.
PDF documentation for npde 3.0: https://github.com/ecomets/npde30/blob/main/userguide_npde_3.0.pdf
data(simtheopp) # Plotting the simulated data for subject 1 in the first simulation plot(ysim[2:12]~xsim[2:12],data=simtheopp,xlab="Time after dose (hr)", ylab="Theophylline concentration (mg/L)",type="l", main="Example of simulated data for subject 1") # Plotting a 90% prediction interval for the observations in theopp # using the simulated data in simtheopp # note : differences in doses between subjects are not taken into account data(theopp) xpl<-c(0,0.25,0.5,1,2,3.5,5,7,9,12,24) xpl1<-list(c(0,0.1),c(0.2,0.4),c(0.5,0.65),c(0.9,1.2),c(1.9,2.2),c(3.4,4), c(4.9,5.2),c(6.9,7.2),c(8.8,9.4),c(11.5,12.2),c(23.7,24.7)) ypl<-cbind(xpl=xpl,binf=xpl,median=xpl,bsup=xpl) for(i in 1:(length(xpl))) { vec<-simtheopp$ysim[simtheopp$xsim>=xpl1[[i]][1] &simtheopp$xsim<=xpl1[[i]][2]] ypl[i,2:4]<-quantile(vec,c(0.05,0.5,0.95)) } plot(Conc~Time,data=theopp,xlab="Time after dose (hr)", ylab="Theophylline concentration (mg/L)") lines(ypl[,1],ypl[,3],lwd=2) lines(ypl[,1],ypl[,2],lty=2) lines(ypl[,1],ypl[,4],lty=2)data(simtheopp) # Plotting the simulated data for subject 1 in the first simulation plot(ysim[2:12]~xsim[2:12],data=simtheopp,xlab="Time after dose (hr)", ylab="Theophylline concentration (mg/L)",type="l", main="Example of simulated data for subject 1") # Plotting a 90% prediction interval for the observations in theopp # using the simulated data in simtheopp # note : differences in doses between subjects are not taken into account data(theopp) xpl<-c(0,0.25,0.5,1,2,3.5,5,7,9,12,24) xpl1<-list(c(0,0.1),c(0.2,0.4),c(0.5,0.65),c(0.9,1.2),c(1.9,2.2),c(3.4,4), c(4.9,5.2),c(6.9,7.2),c(8.8,9.4),c(11.5,12.2),c(23.7,24.7)) ypl<-cbind(xpl=xpl,binf=xpl,median=xpl,bsup=xpl) for(i in 1:(length(xpl))) { vec<-simtheopp$ysim[simtheopp$xsim>=xpl1[[i]][1] &simtheopp$xsim<=xpl1[[i]][2]] ypl[i,2:4]<-quantile(vec,c(0.05,0.5,0.95)) } plot(Conc~Time,data=theopp,xlab="Time after dose (hr)", ylab="Theophylline concentration (mg/L)") lines(ypl[,1],ypl[,3],lwd=2) lines(ypl[,1],ypl[,2],lty=2) lines(ypl[,1],ypl[,4],lty=2)
Computes the skewness.
skewness(x)skewness(x)
x |
a numeric vector containing the values whose skewness is to be computed. NA values are removed in the computation. |
If , then the skewness of
is defined as
The skewness of x.
G. Snedecor, W. Cochran. Statistical Methods, Wiley-Blackwell, 1989
x <- rnorm(100) skewness(x)x <- rnorm(100) skewness(x)
Return subset of data from a NpdeData object
## S3 method for class 'NpdeData' subset(x, subset, ...) ## S3 method for class 'NpdeObject' subset(x, subset, ...)## S3 method for class 'NpdeData' subset(x, subset, ...) ## S3 method for class 'NpdeObject' subset(x, subset, ...)
x |
A NpdeData object |
subset |
logical expression indicating elements or rows to keep: missing values are taken as false. |
... |
Additional arguments (ignored) |
a NpdeData object with a subset of the original data
Extracts elements from a NpdeData object
## S3 method for class 'NpdeData' summary(object, print = TRUE, ...) ## S3 method for class 'NpdeRes' summary(object, print = TRUE, ...) ## S3 method for class 'NpdeObject' summary(object, ...)## S3 method for class 'NpdeData' summary(object, print = TRUE, ...) ## S3 method for class 'NpdeRes' summary(object, print = TRUE, ...) ## S3 method for class 'NpdeObject' summary(object, ...)
object |
A NpdeData object |
print |
whether to print to data to stdev |
... |
Additional arguments (ignored) |
A list with elements N (nb of subjects), data (dataframe containing the data), ntot.obs (total nb of observations), nind.obs (nb of observations per subject)
The theopp data frame has 132 rows and 5 columns of data from an
experiment on the pharmacokinetics of theophylline.
theopptheopp
This data frame contains the following columns:
an ordered factor with levels 1, ..., 12
identifying the subject on whom the observation was made. The ordering is
by Time at which the observation was made.
dose of theophylline administered orally to the subject (mg/kg).
time since drug administration when the sample was drawn (hr).
theophylline concentration in the sample (mg/L).
weight of the subject (kg).
Boeckmann, Sheiner and Beal (1994) report data from a study by Dr. Robert Upton of the kinetics of the anti-asthmatic drug theophylline. Twelve subjects were given oral doses of theophylline then serum concentrations were measured at 11 time points over the next 25 hours.
These data are analyzed in Davidian and Giltinan (1995) and Pinheiro and Bates (2000) using a two-compartment open pharmacokinetic model.
These data are also available in the library datasets under the name
Theoph in a slightly modified format and including the data at time
0. Here, we use the file in the format provided in the NONMEM
installation path (see the User Guide for that software for details).
Boeckmann, A. J., Sheiner, L. B. and Beal, S. L. (1994), NONMEM Users Guide: Part V, NONMEM Project Group, University of California, San Francisco.
Davidian, M. and Giltinan, D. M. (1995) Nonlinear Models for Repeated Measurement Data, Chapman & Hall (section 5.5, p. 145 and section 6.6, p. 176)
Pinheiro, J. C. and Bates, D. M. (2000) Mixed-effects Models in S and S-PLUS, Springer (Appendix A.29)
PDF documentation for npde 3.0: https://github.com/ecomets/npde30/blob/main/userguide_npde_3.0.pdf
data(theopp) #Plotting the theophylline data plot(Conc~Time,data=theopp,xlab="Time after dose (hr)", ylab="Theophylline concentration (mg/L)")data(theopp) #Plotting the theophylline data plot(Conc~Time,data=theopp,xlab="Time after dose (hr)", ylab="Theophylline concentration (mg/L)")
This is simulated data, based on real data obtained in a phase II clinical trial supported by the French Agency for AIDS Research, the COPHAR 3-ANRS 134 trial (Goujard et al., 2010). The original study included 35 patients, who received a once daily dose containing atazanavir (300 mg), ritonavir (100 mg), tenofovir disoproxil (245 mg) and emtricitabine (200 mg) during 24 weeks. Viral loads were measured 6 times over a treatment period of 24 weeks (day 0, 28, 56, 84, 112, 168).
virloadvirload
This data frame contains the following columns:
an ordered factor with levels 1, ..., 50 identifying the subject on whom the observation was made. The ordering is by Time at which the observation was made.
time since the beginning of the study (days)
logarithm (base 10) of the viral load (copies/L)
indicator variable (cens=1 for censored data, cens=0 for observed data)
individual predictions
The datasets were generated in a simulation study designed to evaluate the new method proposed to handle BQL data (Nguyen et al., 2011). Data was simulated using a simple bi-exponential HIV dynamic model describing the two-phase decline of viral load during anti-retroviral treatment.
The virload data frame has 300 rows and 4 columns of data. The dataset was then censored at two different LOQ levels (LOQ=20 or 50~copies/mL) to generate two datasets containing different proportions of BQL data, creating the data frames virload20 andvirload50 respectively
The file simvirload contains 500 simulations under the same model. A full version of the simulated data with 1000 simulations can be downloaded from the github for npde3.0: https://github.com/ecomets/npde30/blob/main/keep/data/simvirload.tab
Goujard, C., Barrail-Train, A., Duval, X., Nembot, G., Panhard, X., Savic, R., Descamps, D., Vrijens, B., Taburet, A., Mentre, F., and the ANRS 134 study group (2010). Virological response to atazanavir, ritonavir and tenofovir/emtricitabine: relation to individual pharmacokinetic parameters and adherence measured by medication events monitoring system (MEMS) in naive HIV-infected patients (ANRS134 trial). International AIDS Society 2010, Abstr WEPE0094.
PDF documentation for npde 3.0: https://github.com/ecomets/npde30/blob/main/userguide_npde_3.0.pdf
data(virload) str(virload) data(virload50) # Plotting the data plot(Log_VL~Time,data=virload,xlab="Time (d)",ylab="Viral loads, base 10 log-scale (cp/mL)") plot(Log_VL~Time,data=virload50,xlab="Time (d)",ylab="Viral loads, base 10 log-scale (cp/mL)")data(virload) str(virload) data(virload50) # Plotting the data plot(Log_VL~Time,data=virload,xlab="Time (d)",ylab="Viral loads, base 10 log-scale (cp/mL)") plot(Log_VL~Time,data=virload50,xlab="Time (d)",ylab="Viral loads, base 10 log-scale (cp/mL)")
The warfarin data frame has 251 rows and 8 columns of data containing
data on the pharmacokinetics of warfarin, an anticoagulant drug used in the
prevention of thrombosis and thromboembolism.
warfarinwarfarin
This data frame contains the following columns:
an integer identifying the subject on whom the observation was made
time since drug administration when the sample was drawn (hr)
total dose received by the subject (mg)
warfarin concentration in the sample (mg/L)
observation type (1 for all observations)
weight of the subject (kg)
subject gender (0=female, 1=male)
age of the subject (yr)
The dataset is the PK part of a larger dataset including both warfarin concentrations and prothrombin complex activity (PCA), which measures the decreased coagulation activity resulting from the inhibition of vitamin K recycling, the mechanism of action of warfarin. It contains the concentrations measured in 32 healthy subjects after a single oral dose of warfarin sodium (1.5 mg/kg of body weight). The subjects in the study were sampled at different times over a period of up to 120 hours.
The data is distributed with the Monolix software as a demo for PK/PD modelling. The data has been slightly reformated for R, removing the line at time=0 and filling the amt column with the dose for each subject, following the output of simulx which was used to simulate data from two alternative models to fit this dataset.
Two datasets containing simulated data are associated with the warfarin data. For
each dataset, 1000 simulations of the original data were performed for the computation of npde.
The package contains only the simulated data simwarfarinCov because of size constraints. simwarfarinBase can be downloaded from
the github for npde3.0: https://github.com/ecomets/npde30/blob/main/keep/data/simwarfarinBase.tab
the data in this dataset was simulated according to a base model without covariates: the PK model was a two-compartment model, with first-order absorption and a time-delay. Interindividual variability was modelled as log-normal distributions for parameters Tlag, ka, Cl and V1, and the error model was a combined error model. The parameters were estimated by Monolix.
the data in this dataset was simulated according to a model including several covariates: an age (centered on 30 yr) effect on Cl, a weight (centered on 70 kg) effect on Cl and V1, and a gender effect on V1. The covariate model was built in Monolix.
O’Reilly (1968). Studies on coumarin anticoagulant drugs. Initiation of warfarin therapy without a loading dose. Circulation 1968, 38:169-177.
PDF documentation for npde 3.0: https://github.com/ecomets/npde30/blob/main/userguide_npde_3.0.pdf
data(warfarin) #Plotting the warfarin PK data plot(dv~time,data=warfarin,xlab="Time after dose (hr)", ylab="Warfarin concentration (mg/L)")data(warfarin) #Plotting the warfarin PK data plot(dv~time,data=warfarin,xlab="Time after dose (hr)", ylab="Warfarin concentration (mg/L)")