aubuti wrote: 
> Exactly. Statistical significance is only "significant or not" with
> respect to a particular (and generally arbitrary) cutoff value such as
> 0.01, 0.05, etc. The relevant underlying statistic, the p-value, is
> continuous, not binary. So there is nothing wrong with the "extremely
> high degree" or "barely significant" statements.

A very good point, and worth elaborating.  "Statistical significance"
simply means that we are referring to a particular confidence level that
the findings are due to the treatment and not to other factors.  When we
say "Statistically signficant at the .05 level" we really mean that we
are confident that there is only a 5% chance that the observed effect
was the result of something other than the treatment.  Put another way,
one time out of twenty the observed effect would have been caused by
something else.  "Statistical significance" at the .05 level is not
actually a very high standard.

R.


------------------------------------------------------------------------
RonM's Profile: http://forums.slimdevices.com/member.php?userid=17029
View this thread: http://forums.slimdevices.com/showthread.php?t=97530

_______________________________________________
audiophiles mailing list
[email protected]
http://lists.slimdevices.com/mailman/listinfo/audiophiles

Reply via email to