Re:The Multi-Armed Bandit Problem and Its Solutions (2018)
by jerf on Tuesday February 05, 2019 @04:08PM
(#19089838)
As responses to criticisms of the current scientific method go, "but the current scientific method is the current scientific method!" isn't really that helpful. I know what is; I'm saying it should be something different.
Re:The Multi-Armed Bandit Problem and Its Solutions (2018)
by apo on Tuesday February 05, 2019 @11:59PM
(#19092822)
You wrote: "The name of the game is to increase and decrease confidence in hypotheses by any legitimate statistical method, not to follow "the" method."
The definition I cited says nothing about the particulars - it just enumerates three essential elements.
What would you propose instead as general principles for a scientific method?
"...It involves formulating hypotheses, via induction, based on such observations; experimental and measurement-based testing of deductions drawn from the hypotheses; and refinement (or elimination) of the hypotheses based on the experimental findings. These are principles of the scientific method, as distinguished from a definitive series of steps applicable to all scientific enterprises."
https://en.wikipedia.org/wiki/Scientific_method
There are many ways to implement this method, but if you leave out a single element, you're doing something other than science.