[R] p-value > 1

[Peter Dalgaard]

amor Gandhi wrote:
> Dear all,
> 
> I am trying to use SAMr-library(samr), it gives me p-value = 1.001, any idea why?

Well, the package maintainer might be a better place to ask. (Bring an 
example if you do.)

However, as a generic matter, the result is obviously nonsensical, and 
could be due to a sloppy approximation of a distribution function, or 
maybe it is a (say) Bonferroni-adjusted p-value which is really an upper 
bound for the correct p-value.

Notice, though, that you should only very rarely care about the exact 
p-value. As soon as it is above 0.1, the message is just that you have 
not proven that there is an effect.

-- 
    O__  ---- Peter Dalgaard             Øster Farimagsgade 5, Entr.B
   c/ /'_ --- Dept. of Biostatistics     PO Box 2099, 1014 Cph. K
  (*) \(*) -- University of Copenhagen   Denmark      Ph:  (+45) 35327918
~~~~~~~~~~ - (p.dalgaard at biostat.ku.dk)              FAX: (+45) 35327907