I'm trying to estimate the sample size required to achieve 80% power at a 5% significance level for a superiority study comparing AUC from bioavailability data.
My challenge is the only previous pilot study I found reported mean AUC and standard errors for the raw data and using this with pwr.t.test in R gives the following error.
Error in uniroot(function(n) eval(p.body) - power, c(2 + 1e-10, 1e+09)) : f() values at end points not of opposite sign
Below are means(SE) for the two groups from the previous study:
Group A: 6300(35.6); n=6
Group B: 16750(57.9); n=6
Here's the code I run:
library(pwr) pwr.t.test(n = NULL , d = 119.84, sig.level =0.05 , power = 0.8, type = "two.sample")
Log transformation should be the way to go I reckon, but I'm not sure how to derive the log SD from the raw SD. Any help will be much appreciated.