clinDR (version 2.4.1)

summary.emaxsim: Summary of output of emaxsim

Description

Detailed summary of repeated sampling properties of Emax estimation and comparison with simple pairwise comparisons.

Usage

# S3 method for emaxsim
summary(object, testalpha = 0.05, clev = 0.9, 
                          seSim = FALSE, ...)

Value

The function produces annotated output summarizing the properties of the estimation procedures. The summaries are also returned as an invisible list for extracting results.

Arguments

object

Output of emaxsim

testalpha

Alpha level for a one-sided MCP-MOD trend test

clev

Nominal confidence level for reported CIs

seSim

If TRUE, then simulation standard errors are reported in parentheses. These should be distinguished from standard errors for estimators in the simulation.

...

Other unspecified parameters (none currently utilized)

Author

Neal Thomas

Details

For pairwise comparisons, the 'most favorable pairwise comparison' means the dose with the best difference versus placebo is compared to the population mean response for the selected dose, thus the target value for coverage, bias, and RMSE changes depending on the selected dose.

See Also

emaxsim, print.emaxsim, plot.emaxsim

Examples

if (FALSE) {
## emaxsim changes the random number seed
nsim<-50
doselev<-c(0,5,25,50,100)
n<-c(78,81,81,81,77)

### population parameters for simulation
e0<-2.465375 
ed50<-67.481113 

dtarget<-100
diftarget<-9.032497
emax<-solveEmax(diftarget,dtarget,log(ed50),1,e0)

sdy<-7.967897
pop.parm<-c(log(ed50),emax,e0)    
meanlev<-emaxfun(doselev,pop.parm)  

###FixedMean is specialized constructor function for emaxsim
gen.parm<-FixedMean(n,doselev,meanlev,sdy)  
D1 <- emaxsim(nsim,gen.parm)
summary(D1,testalph=0.05,clev=0.95)
}
# \dontshow{
## emaxsim changes the random number seed
nsim<-3
doselev<-c(0,5,25,50,100)
n<-c(78,81,81,81,77)

### population parameters for simulation
e0<-2.465375 
ed50<-67.481113 

dtarget<-100
diftarget<-9.032497
emax<-solveEmax(diftarget,dtarget,log(ed50),1,e0)

sdy<-7.967897
pop.parm<-c(log(ed50),emax,e0)    
meanlev<-emaxfun(doselev,pop.parm)  

###FixedMean is specialized constructor function for emaxsim
gen.parm<-FixedMean(n,doselev,meanlev,sdy)  
D1 <- emaxsim(nsim,gen.parm,nproc=1)
summary(D1,testalph=0.05,clev=0.95)
# }