Ben Goldacre writes the bad science column for the Guardian. He has a supporting website at http://badscience.net".

I just read his column on relative risk and natural frequency. It provided me with a vocabulary to explain my regular discomfort with statistics masquarading as something meaningful.

"xyz makes you 50% more likely to get abc." Assuming 'xyz' is something like 'chocolate' and 'abc' is 'hideous boils' you might be tempted to alter your behavior in favor of excluding chocolate from your diet.

But what if they showed you real numbers, say out of 10,000 people 2 will get hideous boils, and out of 10,000 chocolate eaters that jumps 50% to, uh, three people.

A 50% increase, and yet, it is a tiny number.

read the article to get clear on why we should all use 'natural frequencies' (ie. actual numbers, 2 vs 3 in the above example) instead of percentages.

This quote flat scares me:

I’m not alone in finding percentages unhelpful, incidentally. There are studies of doctors, and commissioning committees for local health authorities, and people from the legal profession, that show that even people who interpret and manage risk for a living are much more likely to make the wrong decision when information about risk is presented as probabilities or percentages, rather than as natural frequencies.

Even those among us who are charged with interpreting numbers don't do a very good job of interpreting percentages (hah! And even that conclusion abuses the 'studies.' What did they _really_ say?).

My method of managing pictures has certain strengths and certain weaknesses...so now Molly and I both have flickr accounts.

You can see Molly's calendar view here

And Rich's