testnpde {npde}R Documentation

Tests for normalised prediction distribution errors

Description

Performs tests for the normalised prediction distribution errors returned by npde

Usage

testnpde(npde)

Arguments

npde the vector of prediction distribution errors (returned by the functions npde or autonpde with the option output=TRUE)

Details

Given a vector of normalised prediction distribution errors (npde) computed by npde or autonpde, this function compares the npde to the standardised normal distribution N(0,1) using a Wilcoxon test of the mean, a Fisher test of the variance, and a Shapiro-Wilks test for normality. A global test is also reported.

Value

a list containing 4 components:
Wilcoxon test of mean=0 compares the mean of the npde to 0 using a Wilcoxon test
variance test compares the variance of the npde to 1 using a Fisher test
SW test of normality compares the npde to the normal distribution using a Shapiro-Wilks test
global test an adjusted p-value corresponding to the minimum of the 3 previous p-values multiplied by the number of tests (3), or 1 if this p-value is larger than 1.

Author(s)

Emmanuelle Comets <emmanuelle.comets@bichat.inserm.fr>

References

K. Brendel, E. Comets, C. Laffont, C. Laveille, and F. MentrĂ©. Metrics for external model evaluation with an application to the population pharmacokinetics of gliclazide. Pharmaceutical Research, 23:2036–49, 2006.

See Also

npde, autonpde

Examples

#Computing npde
data(theopp)
data(simtheopp)
x<-autonpde(theopp,simtheopp,1,3,4,boolsave=FALSE)

#Testing npde
y<-testnpde(x$npde)

# Not Run
# Assuming the results were saved to a file output.npde
# using the boolsave=T option and namsav="output" (default)
# dat<-read.table("output.npde",header=T)
# testnpde(dat$npde) 

[Package npde version 1.2 Index]