Wednesday, May 21, 2008

Needles in Bigger Haystacks - The Paradoxical Statistics of Terror

While expansive data mining programs meant to find potential terrorists and criminals have long been goals of our law enforcement and intelligence agencies, futurist, science fiction writer and BoingBoing.net blogger Cory Doctorow eviscerates our culture of political fear mongering in a new column for the Guardian, The odds are stacked against us - Our dangerous statistical ignorance simply by crunching the numbers as to these programs' effectiveness.
"Statisticians speak of something called the Paradox of the False Positive. Here's how that works: imagine that you've got a disease that strikes one in a million people, and a test for the disease that's 99% accurate. You administer the test to a million people, and it will be positive for around 10,000 of them – because for every hundred people, it will be wrong once (that's what 99% accurate means). Yet, statistically, we know that there's only one infected person in the entire sample. That means that your "99% accurate" test is wrong 9,999 times out of 10,000!

Terrorism is a lot less common than one in a million and automated "tests" for terrorism – data-mined conclusions drawn from transactions, Oyster cards, bank transfers, travel schedules, etc – are a lot less accurate than 99%. That means practically every person who is branded a terrorist by our data-mining efforts is innocent."

Read the whole article, it's short and makes a great point, and is the perfect answer the next time someone tries to say we need data-mining, or illegal wiretapping, or widespread bank transaction surveillance, or... You get the picture. Statistics are good at making predictions of generic - not specific - cases. Useful as a guide, but never as useful in bringing in a potential perpetrator as hardcore, down and dirty police work. Instead of providing the tools needed for law enforcement and terror prevention, as Doctorow points out it's taking needles in haystacks and burying them in deeper haystacks for our law enforcement and intelligence agencies to sift through.

2 comments:

Bradda said...

Nice post man. I completely agree with all of it. Everyone knows that you need good police work to catch guys that are trying to hide. Setting massive "nets" to collect everyone's info to root out terorists is a joke in and of itself. Like Carlin says, "Americans LOVE a good bullshit story!"

kreplech said...

TSA agents stealing our toe-nails clippers serves more of a purpose than trying to catch the bad guys.

That purpose is most obviously, and most ridiculously believed to be, to deter people from hijacking airplanes. The unlikely event of a hijack proves Doctorow's point quite nicely.

But, there are at least three other reasons behind our toe-nail clipper laws.

1) To make people feel safe our government has begun these massively high-profile campaigns (mostly high-profile because of how obnoxious they are). I truly do feel safe enough to know that when I fall asleep on the red-eye flight to miami, i won't wake up with shorter toenails.

2) To make people believe that the government is doing or is capable of doing something about people who would like to attack us with toe-nail clippers. truthfully, we've already had a shoe-bomber, the next guy is likely to be a little more creative than to try the shoe-trick again. let's stop taking our shoes off before we get on airplanes.

3) To remind us of the ever-present threat that the toe-nail clipper murderer/hijacker/rapist/computer hacker represents. They believe that without having our belongings stolen from us at the airport, we might stop believing that there are shady, and most likely muslim, characters our there who think of little else than concocting complex and unlikely schemes to end our lives.

the most frustrating thing is, the last one appears to be working. just as there are 9-11 conspiracy lunatics out there, there are people who believe that we are unsafe.

let's put them all on the next flight to mars.