Understanding Drug War Statistics
 
How the government justifies and makes drug policy with junk science, by misrepresenting data, and by using statistical trickery

1. Declare a Perpetual Crisis - "It is crucial that one thoroughly grasp the most robust trend in addiction epidemiology: drug use has dramatically declined over the past thirty years. Past month use rates are literally half of what they were in the 1970's, and there has been virtually no change in past-month drug use for over a decade."
[Printer Version - PDF]
 

2. Big Lies & Bullies Trump Researchers in the War on Drugs -- "The message to doctors and to researchers was clear. Expect to be attacked by federal law enforcement and abandoned by your peers in the powerful AMA for your professional efforts and honesty."
[Printer Version - PDF]
 

3) Junk Science Drives Policy -- "What we have here is nothing less that the incorporation of bogus data into a federal law in order to justify mandatory drug testing for government employees in pursuit of the impossible 'Drug-Free Workplace.'" [major revision June 20th]
[Printer Version - PDF]
 

 4)  Outcome Obfuscation -- "A sort of statistical sleight of hand, Outcome Obfuscation is a misleading confusion of outcome and index event."
[Printer Version - PDF]
 

5)  Denominator Abuse and the Chilling Effect -- "We are talking about risk here and the appropriate statistic is a rate. The Numbers in the [DEA] table can correctly be used as numerators to compute this statistic, however, 'Total DEA registrants' is NOT the appropriate denominator because the denominator must include only physicians who could possibly come to DEA attention. I call this misleading use of an incorrectly computed rate "Denominator Abuse."
[Printer Version - PDF]
 

REVISED! 2005-11-04 

6)  Flash Trash -- "The use of suggestive of provocative numbers or statistics, usually presented as true prima facie, which when analyzed  using algebra, do not in fact support the implied conclusion."
 
[Printer Version - PDF]
 

 7)  Shock Schlock -- "Shock Schlock is the presentation of lurid or otherwise shocking anecdotes in lieu of meaningful data and sober statistical analysis."
[Printer Version - PDF]