[R] power.t.test

[Peter Dalgaard BSA]

Hank Stevens <HStevens at muohio.edu> writes:

> power.t.test() requires a standard deviation as input, but for a two
> sample test, I do not understand what is required. Is it the standard
> deviation of the means (standard error), or of the combined sample?

The two (theoretical) distributions from which samples are drawn are
assumed to have the same SD. This is the value to plug in.

-- 
   O__  ---- Peter Dalgaard             Blegdamsvej 3  
  c/ /'_ --- Dept. of Biostatistics     2200 Cph. N   
 (*) \(*) -- University of Copenhagen   Denmark      Ph: (+45) 35327918
~~~~~~~~~~ - (p.dalgaard at biostat.ku.dk)             FAX: (+45) 35327907