Comments on: A small victory for scientific gobbledygook, arithmetic and Nate Silver

By: Tom Fid

Tom Fid — Fri, 16 Nov 2012 14:56:43 +0000

Bruce – Making stuff up is also vastly cheaper and easier than processing large amounts of data, so it works for both sides of the bottom line if it works.

Cherilyn – Interesting. I wonder if Lichtman’s forecasts have been formally published in advance? Anyway, nice to have a moment when the press takes note of the tide of BS.

By: Cherilyn

Cherilyn — Fri, 16 Nov 2012 13:48:02 +0000

All hail Nate Silver! Mathiness over truthiness!

I am deeply amused by his new celebrity status over faithfully crunching numbers. When was the last time that happened?

On the subject of forecasting fun, I also liked this piece.
http://m.npr.org/news/front/164711093

By: A small victory for scientific gobbledygook, arithmetic and Nate Silver | Sytems Dynamics and Policy | Scoop.it

Sun, 11 Nov 2012 04:02:56 +0000

[...] Nate Silver of 538 deserves praise for calling the election in all 50 states, using a fairly simple statistical model and lots of due diligence on the polling data. [...]

By: Bruce Skarin

Bruce Skarin — Fri, 09 Nov 2012 17:26:59 +0000

It’s not just ego. It’s marketing. If a pundit can dismiss data in a way that at appears believable to at least part of the masses, then you can market whatever idea you want. People like to be able to say they picked the winner. I think pundits systematically dismissed the forecasts in order to make it as close as possible.

It’s of course impossible to verify,but I bet if pundits had conceded that Obama was likely to win, it wouldn’t have been anywhere near as “close” as it ended up being. Perhaps there is a study that given a 50-50 shot, would you vote versus a 10-90 shot. It looks like this study may control for the effects of “wishful thinking” though I do not have access to it.
http://poq.oxfordjournals.org/content/76/3/538.abstract