[R] Lilliefors Test

Peter Dalgaard p.dalgaard at biostat.ku.dk
Mon Oct 20 20:01:04 CEST 2003


Martina Pavlicova <pavlicov at stat.ohio-state.edu> writes:

> > Is it not true that the Shapiro Wilks test implemented in the package
> > ctest requires the assumption that the population variance of the
> > variable is known?
> 
> I am not sure about this one...

No, that is false. Shapiro-Wilks basically measures the correlation in
a qqnorm() plot (too far below 1 and the distribution is deemed
non-normal) which is a  scale- and position-invariant measure.

-- 
   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




More information about the R-help mailing list