Themis;352994 Wrote: > Can you, if you don't mind, link us a couple of examples of such > studies, so we could discuss ?
Several are given in the paper. I'm sure there are many, many more - for example, as people develop lossy compression algorithms this must be one of the things they check for. DeVerm;353052 Wrote: > I am not familiar with the ANOVA method nor Fishers' PLSD test they used > (just an example of many methods and tests used) but when they state > that these combined are okay for assessment of the statistical > significance, one should be very familiar with these methods and tests > plus have access to all the data collected and calculations performed > before stating that it's flawed. Everybody that's ever done anything with stats is familiar with ANOVA. Fisher's PLSD isn't relevant for this question - it's not a test of statistical significance. And I agree with lanierb - they are indeed treating multiple measurements on the same individual as statistically independent. For example, in the Results section under EEG Experiment 1, they state that 11 subjects participated. But they use F(2,63) to evaluate the significance, presumably because they took multiple measurements on each individual (although they don't explain). As lanierb points out, that's invalid unless something else is going on (which they haven't mentioned). And had they used F(2,11) the result would not be significant even at the 5% level. -- opaqueice ------------------------------------------------------------------------ opaqueice's Profile: http://forums.slimdevices.com/member.php?userid=4234 View this thread: http://forums.slimdevices.com/showthread.php?t=54077 _______________________________________________ audiophiles mailing list [email protected] http://lists.slimdevices.com/lists/listinfo/audiophiles
