function to generate data from a Beal model with fixed effects
simulateBealModelMixedEffects(
numSubjects,
clearance,
volumeOfDistribution,
dose,
varCompClearance,
varCompVolumeOfDistribution,
timePoints
)scalar, number of subject which should be generated
scalar, clearance
scalar, volume of distribution
scalar, dose
scalar, standard error of the normal distribution generating clearance
scalar, standard error of the normal distribution generating volume of distribution
vector of time points
generated sample with numSubjects as the number of rows and length of timePoints as the number of columns
The model used to generate data at time t is as follows $$y(t)=C(t)\exp(e(t)),$$ where \(C(t)\), the PK-model, is defined as follows: $$C(t) = \frac{\mathrm{dose}}{V_d} \exp{(CL.t)},$$ with \(V_d\) the volume of distribution and \(CL\) as clearance. The error model is consdiered as \(e(t) \sim N(0, h(t))\), with: $$h(t) = 0.03 + 0.165 \frac{C(t)^{-1}}{C(1.5)^{-1} + C(t)^{-1}}.$$ For the mixed effects model, \(CL=\widetilde{CL} \exp{(\eta_1)}\), and \(V_d=\widetilde{V_d} \exp{(\eta_2)}\), where \(\eta_1 \sim N(0, w_1^2)\) and \(\eta_1 \sim N(0, w_2^2)\). Note that \(w_1\) and \(w_2\) are specified by varCompClearance, and varCompVolumeOfDistribution in the arguments, respectively.
Beal S. L., Ways to fit a PK model with some data below the quantification limit, Journal of Pharmacokinetics and Pharmacodynamics, 2001;28(5):481<U+2013>504.
# NOT RUN {
set.seed(111)
simulateBealModelMixedEffects(10, 0.693,
+ 1, 1, 0.2,0.2, seq(0.5,3,0.5))
# }
Run the code above in your browser using DataLab