PPRuNe Forums - View Single Post - WSJ article: On Asia’s flights, potentially dangerous mistakes go unreported
Old 19th Jul 2015, 11:43
  #31 (permalink)  
roulishollandais
 
Join Date: Jun 2011
Location: france
Posts: 760
Likes: 0
Received 0 Likes on 0 Posts
Snoop

When we read about statistics in public media and in highest level works too, it is very seldom that the distribution law is refered to.
Pure nonsense for the whole work.

If random is refered to in such works, we see another mistake in stats'use : non only we suppose without demonstration that the distribution is Gaussian , but the number of similar observations is often to low.

Everyday I'm angry listening on radio/TV the met forecast, ie :"Temperature is 5°c lower than normal (Gaussian) in that season " (temperature and season undefined and shifting everyday...).

Trusting in stats applied in respect of the stats'rules, I understand the stats'bashing but false "you may let stats say everything you want".
roulishollandais is offline