search

rpact-com / rpact

rpact: Confirmatory Adaptive Clinical Trial Design and Analysis
https://rpact-com.github.io/rpact/
23 stars 5 forks source link

print() output: value of bindingFutility not correctly displayed #41

Closed gwassmer closed 4 months ago

gwassmer commented 4 months ago
Dear Professor Wassmer,
I am a statistician working for a pharmaceutical company named Zelgen.  Please allow me to take this chance to thank you for your great work in authoring "Group Sequential
and Confirmatory  Adaptive Designs in Clinical Trials" and issuing the powerful R package "rpact".  If you don't mind, may I consult you on below question ? Thanks in advance.

When I was running below codes to get boundaries, I found that designtest1 indicated that futility bound was non-binding. I understand bindingFutility=FALSE is the by default value.  However,  powertest1 showed that the design parameters of futility bounds was "Futility bounds (binding) ". It seems inconsistent with the designtest1.  Not sure if this is a typo ?  Also, any impact on the efficacy bound although I did not find any discrepancy?  

designtest1 <- getDesignGroupSequential(
                        sided = 1, alpha = 0.025, beta = 0.2,
                       informationRates = c(205 / 387, 285 / 387, 1), 
                       typeOfDesign = "asOF",typeBetaSpending="bsOF"
    )
designtest1

powertest1 <-getPowerSurvival(designtest1,
                              lambda1 = log(2) / 18, lambda2 = log(2) / 12,
                              dropoutRate1 = 0.05, dropoutRate2 = 0.05, dropoutTime = 12,
                              accrualTime = 0, accrualIntensity = 25, maxNumberOfSubjects=500,
                              maxNumberOfEvents = 387, directionUpper = FALSE
)
powertest1

Look forward to hearing from you. Thank you again!

Jack Peng

Suzhou Zelgen Biopharmaceuticals Co., Ltd.

https://www.zelgen.com/en/
Email:  pengmy@zelgen.com