[R] Testing for randomness

Peter Dalgaard BSA p.dalgaard at biostat.ku.dk
Thu Apr 17 14:21:21 CEST 2003


"Liaw, Andy" <andy_liaw at merck.com> writes:

> It's hard to tell what you're looking for.  There are some white noise tests
> in time series, some of which, I imagine, are implemented in some of the
> time series packages for R.  There are tests for quality of pseudo-random
> number generators, probably the best known being Marsaglia's DIEHARD battery
> of tests.  You can find them by googling.  They are not in R, though, AFAIK.

...and given that we have just discarded one of Marsaglia's generators
as the default RNG in R, some critical sense probably needs to be
applied to his test battery as well!

-- 
   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