On Fri, Sep 16, 2011 at 10:23 AM, Viktor Cerovski <[email protected]> wrote: > stddev 1e12 + x - 0.5 > 0.288938 > > Same x translated by tiny (compared to 1e12) 0.5, > still large mean and the problem is gone. > > So, what you suggest is the correct remedy, but for the wrong > reasons.
I think you are arguing that there's a threshold effect here. But I do not see how this non-linearity makes my reasoning wrong. -- Raul ---------------------------------------------------------------------- For information about J forums see http://www.jsoftware.com/forums.htm
