OK - I'll admit it - I did engage in a little bit of hyperbole.

But you have to admit that "at best worthless" has a better ring to it than "at best, when combined with a qualitative analysis of the model itself, and some testing with out of sample data, can be a useful tool in decision making".

You are right that no investment bank will go anywhere near this.

When I used to work in the financial services industry we used to call this "data mining". The result is usually at best worthless and at worst dangerous as it is so often misused.

It's worth remembering the saying with data: "if you look hard enough, you can find anything you want to".

It's not true that there have been only four hijackings for the purpose of killing everyone on board. A Fed-Ex flight was almost hijacked by a ride-along pilot and crashed so his family would get insurance money. Samuel Byck in 1972 tried to hijack a plane to try and crash it into White House, and Algerian hijackers took Air France Flight 8969 in 1994 and are believed to have been planning to use it as a flying bomb.

Another disputable claim is that most hijackings are done by well-trained terrorist groups. A lot of them are done by solitary idiots and looneys; a notorious disaster was caused when an African plane was hijacked and the hijackers refused to understand that it didn't have the fuel to take them to Australia.

More importantly, while guns would be a bad thing, even with no guns, I doubt many hijackers will be successful any more. Oh yes, Mr. Hijacker, I trust you that you aren't just going to kill us all. But you know, I would trust you a lot more after we kept you out of the cockpit and we broke a few bones of yours for good measure. You've got a bomb; even if you're telling the truth, why should we trust you not to use it?

Why not mount the switches so they are flush with the edge of the case rather than having that unslighly mess of millions of cables?