The GMO plot thickens, in a funny way. I thought that the GMO "experts" are making errors in logic and risk but I realize they do not understand their own claims in their research and contradict them. Many are critical on our focus on "absence of evidence" as "nonscientific" yet their own work is based on this approach (that is, put the weight on the side of absence of evidence)... I repeat, in their own works. Their papers need to abide by a certain statistical procedure yet most don't know what it is about. Looks like they hire some staff person to process data or use some opaque (to them) computerized procedure .
---
For standard statistical theory doesn't allow "acceptance", it only allows "failure to reject". Even when someone in prose says "accept that" he mathematically means "failed to reject at some significance level...", i.e., "BARRING A TAIL EVENT". Similarly, when someone is indicted, he is treated as innocent unless proven otherwise. This principle is adopted by scientific journals (remember that statisticians are the "evidence" police). This is a big thing and it is ironic.
---
The biologists after us don't appear to be aware of the central fact that evidence = "barring a tail event" and argue they have "evidence there can't be a tail event". The fact that statistics is hard for scientists AND they need to use it (as part of their own canon) means they rely on computers or some statistician who happens to be passing by... We mentioned that >50% of published neurobiology papers in "prestigious" journals making comparisons make an elementary (but severe) statistical mistake. But it looks like things are a lot, a lot worse.
---
P.S. As I show in SILENT RISK, acceptance can be done but it needs to be nonprobabilistic s.a. "there exists at least one black swan as I have seen one". As such it is never part of hypothesis testing.
https://www.facebook.com/13012333374/posts/10152632226883375/
Articles
Aucun commentaire:
Enregistrer un commentaire