Perhaps because you don't want to because you still can't cite actual example of audio DBT not revealing audible difference that was really there.
Your attempt to smear audio DBT by implanting doubts, is so overused by professional shills that it's boring.
More of the same dancing around, just like the professional shills do on internet forums.
Even--Jakob is being thorough about experimental/statistical methodologies and, as result, coming across as frustratingly pedantic.* There's a wide difference between that and shilling, though. I don't see him trying to sell a different, more favorable brand of testing, but simply asking for rigor.
* And goodness knows we need sober, ostensibly pedantic, people to grind forward with progress as the more hyperbolic folks fly off.
To the point, while this is in medicine, the message remains the same regardless the field: PLOS Medicine: Why Most Published Research Findings Are False
Very, VERY few studies within audio land would qualify as large and well controlled, and, shockingly, they tend to show how "deaf" we are rather than how incredibly good our hearing is. (Remember my prior disclosure and bias)
* And goodness knows we need sober, ostensibly pedantic, people to grind forward with progress as the more hyperbolic folks fly off.
To the point, while this is in medicine, the message remains the same regardless the field: PLOS Medicine: Why Most Published Research Findings Are False
Very, VERY few studies within audio land would qualify as large and well controlled, and, shockingly, they tend to show how "deaf" we are rather than how incredibly good our hearing is. (Remember my prior disclosure and bias)
Just because http://webpages.charter.net/fryguy/Amp_Sound.pdf
is old doesn't mean its invalid or irrelevant.
OK, certain well known high end writers (some head us well-known and profitable high end publications) don't like it and dismiss it based on some grounds that are either based only on their personal authority, or some made up or otherwise specious grounds.
What we seem to have here seems to be a true believer that will dismiss any evidence that goes against his prejudices, pure and simple.
Hint: There will never be a real world DBT that some internet troll, some place, will not dismiss on specious grounds.
Having read many of his posts, it appears that he's being true to his personal prejudices.
While he personally may not be a shill, it appears that he's citing them as infallible authorities.
It can only be looked at as a clever piece of satire.
The only statistical valid statement that can be made is that in the tests no differences were detected. That cannot be extended to there were no differences. The test is not that powerful.
dave
There are numbers of differences and I would like to know specifically which, so let me ask you, what kind of differences are you referring to?
Agreed, but that is a truism.
Agreed, but that is a truism.
Proving a negative hypothesis is difficult or impossible, and generally impossible.
I don't know of any test that can reliably prove every negative hypothesis, do you?
You said "differences". There are number of differences and I would like to know specifically which, so let me ask you, what kind of differences are you referring to?
And I was asking you what kind of differences. Can't you just give a straight answer? 🙄 BTW, straight answer includes "don't know".
What say you?
The test claims no differences, so any differences would count. You didn't get that right off the bat?
dave
dave
Figure of speech.
For example, there is a hypothesis that I can run a mile in a minute. We know that we can collect as much evidence as we want showing that it is not true. No human has ever run a mile in a minute, and the evidence we have to date suggests oh so strongly that this is practically speaking, a physical impossibility.
How much evidence of me failing to run a mile within a minute do we need to collect until we give up and say the hypothesis is false?
if you are a true pedant, you would probably say that the hypothesis can never be proven false. Back in the real world...
It can't be. And i know enuff about statistics to know how hard it is to do a proper unbiased blind test. If you want to believe Clark's tests go ahead... it is just more noise AFAIC.
Have a look at Kunchar's papers. How many times did he get a null test until he sorted his ABX test, and then proved that the limit of human time perception is less than 5µs.
dave
That depends on what kind of difference you are talking about.
You don't know that, especially when you couldn't come up with one example I mentioned in my last sentence here.