View Single Post
  #195  
Old 10-15-2018, 09:02 AM
Damuri Ajashi is offline
Guest
 
Join Date: Jul 2006
Posts: 20,376
Quote:
Originally Posted by Kimstu View Post
The footnote in the linked article indicates that they took the small sample size into account, and still came up with a range of 10% to 40% for the risk ratio, with a 95% confidence level:

So, while it may not be statistically valid to claim black teens are exactly 21 times as likely to be killed by police as white teens, it is statistically valid to say that black teens are anywhere from 10 to 40 times as likely to be killed by police as white teens.
Didn't the statistician withdraw his support?