opaqueice;353711 Wrote: 
> ...the most common is when data points are not independent but the
> analysis assumes they are...

Unfortunately, _proving_ independence in the general case is not
possible... often researchers will assume independence if it seems
"reasonable" to do so, in their opinion (which is often incorrect)...

opaqueice;353711 Wrote: 
> ...it's really, really, really hard to account for all possible
> confounding factors 

In fact since many may be lurking, it is impossible to even identify
all of them - let alone account for their influence(s).

Statistics can be a most unsatisfactory science, but it is the best we
have to work with.  Usually it should be viewed (and used!) with a VERY
high degree of skepticism.  :)


-- 
NewBuyer
------------------------------------------------------------------------
NewBuyer's Profile: http://forums.slimdevices.com/member.php?userid=7862
View this thread: http://forums.slimdevices.com/showthread.php?t=54077

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

Reply via email to