Do you see any issues with MBI being used after this commentary? Apart from just not using standard paradigms.
At its core did the MBI method as originally done meet the criteria to make the method fit for its common usage in sports science.
Second to this, as MBD is formed now (as in, the spreadsheets that can be downloaded from the website) or are @Sander comments more along the lines of.
MBI/MBD doesn’t stand up to standard statistical rational but it can be ‘‘salvaged’’ only after the following changes are applied (which are yet to be done)
There are hundreds of currently cited studies using MBI and possibly hundreds more that didn’t cite using MBI out of fear of something (but used the method to come to its conclusions) for example
It seems that sports scientists (those that use MBI/MBD) are using @Sander comments here to suggest that everything is fine with MBI/MBD which is a little bit weird, because I read his comments as MBD could be OK but only after changes are made (which at this stage is yet to happen)
Thank you @sander for your commentary.
The issue for me being an untrained statistician, is that I read comments like yours, and see the online sports science community take them on board as suggesting that because of the above comments MBI/MBD as being used current and beforehand (with regards to MBI) is perfectly fine.
Which is to say it goes against the stronger statements below
"That review, Professor Welsh says, was damning: MBI did not work when compared with accepted principles of statistics.
“They are claiming to have found effects that very likely are not real,” says Professor Welsh.
“It’s increasing the chances of finding an effect that is not there,” says Dr Knight."
“If I was ever to peer review a paper using magnitude-based inference then I would reject it and tell the authors to completely redo their analysis,” says Professor Adrian Barnett, president of the Statistical Society of Australia.”
Or @f2harrell comments
Do you think that the current implementation as used, currently today as communicated here
sportscience.sportsci meets standard statistical practice. Or are you saying that once Hopkins and Batterham make the suggested changes by yourself, Lakens that then once MBD is ‘‘salvaged’’ and in its ‘‘final form’’ should sports scientists (typically untrained in statistics) use MBD
Once again thank you,
I am sure this seems like a lot of questions, but honestly its such a big topic that the community now seems to be getting one set of answers vs another.