jkeny wrote: 
> Sorry, loose terminology - what I mean is "fail" to be able to
> differentiate between the two devices/samples - getting a null result or
> a result statistically close to random guessing.

As many of the heated arguments seem to stem from loose terminology, I
think it is good to strive towards using precise terms. A test like this
only fails if it doesn't provide any information at all - it is so badly
designed or executed that the results are totally inconclusive. What you
are talking about is "failing to disprove the null hypothesis". 

I think we also need to be clear about the purpose of the test and the
possible results. Even in the best of cases, all it will do is providing
a single data point. It won't "prove" anything, or establish the
"reality" of anything - it will be another small piece of evidence. For
a more general conclusion, approaching "proof" of anything, the test
results need to be independently replicated, under controlled
conditions, and enough times to provide real statistical relevance.



"To try to judge the real from the false will always be hard. In this
fast-growing art of 'high fidelity' the quackery will bear a solid gilt
edge that will fool many people" - Paul W Klipsch, 1953
------------------------------------------------------------------------
Julf's Profile: http://forums.slimdevices.com/member.php?userid=42050
View this thread: http://forums.slimdevices.com/showthread.php?t=96407

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

Reply via email to