Bioequivalence and Bioavailability Forum

Dear Detlew,

that’s really a gem!
I wasn’t aware that 1.1-13 is already on CRAN. See also some remarks I just added to my previous post about a CL of the GMR.

---

Edit: Some additions…

❝       # stepwise growing vectors is R-Inferno Circle 2

❝       # but here we dont know the dimension in advance. Right?

Unavoidable.

Sometimes people don’t know which version they (or their IT guys) installed. Maybe it’s safer to replace

    # can use allways power2.TOST() if PowerTOST V1.1-13 is used
    # else an if() construct is necessary switching to power.TOST()
    # in case of des=="paired"
    pwrN <- power2.TOST(CV=CV, n=n, theta0=GMR, design=des)

by

    if(packageVersion("PowerTOST") < "1.1.13" & des == "paired") {
      pwrN <- power.TOST(CV=CV, n=Ns[j], theta0=GMR, design=des)
    } else {
      pwrN <- power2.TOST(CV=CV, n=n, theta0=GMR, design=des)
    }

Most input errors are already trapped by PowerTOST. At the beginning of Sens() add:
  if(pwr.min < 0.05) stop("Minimum acceptable power must not be <0.05!")
… otherwise uniroot() throws an error.
Consider adding ... to transfer optional parameters (theta1,…).

Tested:
R 3.0.2 (2013-09-25), PowerTOST 1.1-12 (2014-07-02) on 32bit Vista Business SP2
R 3.1.1 (2014-07-10), PowerTOST 1.1-13 (2014-08-12) on 64bit Win7 Pro SP1

---

Sneak Preview





To do: Explore the loss of power caused by lower variability. Very important for scaling. In the plots I have set the lower limit to 50% of the expected CV.