Meaningful Relationships

Our predictions may be more prone to failure in the era of Big Data. As there is an exponential increase in the amount of available information, there is likewise an exponential increase in the number of hypotheses’ to investigate. For instance, the U.S. government now publishes data on about 45,000 economic statistics. If you want to test for relationships between all combinations of two pairs of these statistics—is there a causal relationship between the bank prime loan rate and the unemployment rate in Alabama?—that gives you literally one billion hypothesis to test.

But the number of meaningful relationships in the data—those that speak to causality rather than correlation and testify to how the word really works—is orders of magnitude smaller. Nor is it likely to be increasing at nearly so fast a rate as the information itself; there isn’t any more truth in the world than there was before the Internet or the printing press. Most of the data is just noise, as most of the universe is filled with empty space.

Nate Silver, The Signal and the Noise

The strange case of the surveillance cameras

This is the story of a statistic; it is sort of a detective story.

The mystery stat was sitting on one of our Times blogs and read “the average Brit is caught on security cameras some 300 times a day” and, God knows why, I just decided to chase the number down and find out where it came from.

The source was given in a footnote as coming from a book The Maximum Surveillance Society, published in 1999, by two academics, including a C. Norris.

So I set to work trying to find the book. In the meantime I mused on two things. First was how the “300 times” had become viral. It now occurs all over the place, and is the standard statistic used for the number of times Britons may or will be captured by cameras daily.

I managed to find a copy of the Norris book online. The footnoted page was towards the back of a chapter detailing a day in the life of a man called Thomas Reams, as he did various things in and around London. The authors wrote “While this contrived account is, of course, a fictional construction, it is a fiction that increasingly mirrors the reality of routine surveillance.”

What? A fiction!

Imagine, for a moment, that the original paragraph had read “and one hypothetical construction managed to have its fictional hero captured 300 times in a single day”. It wouldn't be quite the same, would it? So I began to wonder how the report's authors had failed to notice that an important factual source was fictional. Had they not checked it?

Professor Norris reminded me that the viral 300 - still based on his book - entered the bloodstream long before 2006. And he was right. For example the BBC website carries a 2002 story stating that “the average citizen in the UK is caught on cameras 300 times a day”.

So, that was the story of one statistic in one study.

Every day we hear of several statistics, and every week of several studies. I have no idea whether the “300 times” case is typical, but I fear that it might be, and that, if only there were more time to scrutinise all the claims made in such “reports” - whatever side they take - we would discover many “truths” that just aren't.

David Aaronovitch
(London) Times