Spinning Speed Camera Stats

[RobBrady]

Benjamin Disraeli famously said: "There are three kinds of lies: lies, damned lies, and statistics."

The Department for Transport (DfT) released figures earlier in the week which gave details of the perceived effectiveness of some speed cameras. These figure were drawn from local authorities who recently started publishing data on accidents and casualties on particular stretches of road before and after the installation of speed cameras in their particular areas.

The national press picked up on this with headlines from The Telegraph such as "Speed cameras fail to cut accidents" and "Speed cameras do not cut accidents... they create them, study finds" from the Daily Mail. It wasn't a study by the way, it was just a release of simple data.

However, some may feel that the Guardian have produced a more measured reaction to the story headlined: "So speed cameras can cause accidents? The maths just doesn't add up".

They argue that, statistically speaking, random factors could lead to a situation where the number of accidents increase after the installation of a speed camera saying "This will happen even if the probabilities of an accident happening have actually gone down".

Over the years, there's been a lot discussion about the regression to mean effect and randomness when it comes to speed camera statistics- usually from those trying to prove that speed cameras don't work. It's interesting to find an argument that attempts to prove that these factors have a part to play in explaining why cameras are effective overall even if they don't appear to work in certain places.
_________________
Robert Brady
Editor, Pocket GPS World
The Premier GPS / SatNav Resource for News, Reviews and Forums

[JimmyTheHand]

"What is sauce for the goose is sauce for the gander." - if the speed camera industry uses statistics in a naive way to justify them then they should expect the same back
_________________
J.

[mostdom]

Sensationalized headlines from the Mail and telegraph. Obviously couldn't help themselves!
_________________
Dom

HERE LIES PND May it rest in peace.
Navigon 7310/iPhone Navigon&Copilot

[JQL]

The Gaurniad is biased as well. The Maths does add up.

Case in point. About one month ago, following an out-of-town car at about 5mph below the posted speed limit, on a dual carriageway, when the driver spots a TAX camera. So what does he do?

Slams on his brakes and I mean slam them on. His speed drops by nearly 50% to below 40mph! As I was riding my motorcycle, I had no problems slowing down. The car driver behind me though, nearly rear-ended me. I only avoided being rear-ended by lane-splitting (luckily the middle lane had sufficient space to do this).

This is not the first time it has happened to me and, when it happens again and, if I do get hit (and survive), I will be suing whoever installed the camera and its operator.

TAX Cameras, for the most part, are dangerous, revenue generating devices and only a very small number are actually safe or for safety.

What is needed is a visible Police presence. That's much more effective at slowing drivers down.
_________________
John

E-TEN M700 with TomTom

Free Avatar Sizing software Avatar Sizer

We see you’re using an ad-blocker. We’re fine with that and won’t stop you visiting the site.
Have you considered making a donation towards website running costs?.
Or you could disable your ad-blocker for this site. We think you’ll find our adverts are not overbearing!