Tuesday, August 28, 2007

The Wisdom of Crowds: The verdict

Hello, and thanks for holding your breath... after 11 days away I am ready to reveal how many emails were in my inbox on my return - and yes it is proof of the wisdom of crowds.

Regular readers of this blog, and my facebook friends, will recall that just before I went away I asked for your estimates on how many emails would be in my inbox this morning.
I managed to confuse the issue by saying I was away for 9 days on facebook - where the guestimates were listed.

So, I've taken the liberty of calculating the average number of emails per day and adjusting the result to take account of my initial bit of misdirection.

The guesses ranged from (for nine days) 7 and 56(yes really) to 432,215 (again, yes, really).
So I removed those extremes from the calculation.

The range I was left with started at 180 and went all the way up to 1000 ( a late arrival sent as a comment on this blog while I was away).

Adjusting for the 9-day/11-day initial cock-up, I ended up with an actual figure of a spookily round 500 emails clogging my inbox.

And the crowd guess?

461. Just 39 off. A margin of error of less than 10%. This from a group of people who know very little about my average email intake!

And most impressively, this average figure is closer to the actual result than even the best single guess (Closest by a smart individual was Benedikt Hanswille Benedikt Hanswille: 550).

Just goes to show - none of us is as clever as all of us!

Update: Aug 31. In yet another spooky coincidence (see The Increasing Incidence of Coincidence) regular contributor BadgerGravling made a wild stab in the dark at how many emails I'd get, but posted it somewhere we both forgot... until now. It seems one of us is cleverer than all of us because he got it absolutely bang on: 500 on the nail!

Let's assume he's the exception that proves the rule...


The rate of change is so rapid it's difficult for one person to keep up to speed. Let's pool our thoughts, share our reactions and, who knows, even reach some shared conclusions worth arriving at?