Re:The Problem with Feedback
by taeric on Tuesday December 04, 2018 @10:47PM
(#18605549)
If you are scanning historic data looking for correlations, you will almost certainly fall for some of the same traps that are common in p hacking.
Now, can you mitigate some by carefully doing an experiment again? Certainly. But you should also not constrain experiments to only things to have been measuring already.
Now, can you mitigate some by carefully doing an experiment again? Certainly. But you should also not constrain experiments to only things to have been measuring already.