Do we need this junk?

Mon Apr 9 21:30:32 UTC 2007

On 4/6/07, Nikolas Britton <nikolas.britton at gmail.com> wrote:
> On 4/5/07, Erik Trulsson <ertr1013 at student.uu.se> wrote:
> > >
> > > 98.83% of us have at least a i686 and 62.6% of us have at least a i786
> > > (SSE2) processor.
> >
> > And 73.45% of all statistics are mainly made up of hot air.
> >
> ...
> >
> > What makes you think those stats are even half-way accurate or
> > useful.  It is probably a highly biased sample.
> >
>
> I don't appreciate being called a lier. Maybe you should step up to
> the plate if you don't believe my statistics.
>

So you aren't a liar.  We'll just assume you don't know much about statistics.

[...]
>
> Data source: http://www.bsdstats.org/cpus.php

Self-selecting samples are always biased, and statistics generated
from them tend to be meaningless.  The numbers at bsdstats.org can
only provide minimums, not maximums (i.e. "there are at least N 486
systems in the world running FreeBSD", not "there are no more than N
486 systems in the world running FreeBSD"), and are useless for this
sort of argument.

- Bob