The Errors of Political Punditry

Philip Tetlock at The Edge briefly reviews his 30 year study of political forecasting, upgrading his opinion from his 2005 book with the opinion that accurate predictions are possible in the near term, if you work hard at it. Here’s a summary:

So, we found three basic things: many pundits were hardpressed to do
better than chance, were overconfident, and were reluctant to change
their minds in response to new evidence. That combination doesn’t
exactly make for a flattering portrait of the punditocracy.

The article includes a nice gloss on the Nate Silver “controversy” [Forbes] in the forecasts prior to the recent presidential election and the way professional pundits — generally using far less rigorous methods than Silver and seeking popularity rather than accuracy — insulate themselves from their predictions.

Much of the article describes a project of The Intelligence Advance Research Projects Agency to measure the accuracy of predictions on a level playing field, a bold project because it could easily show that forecasters at the top of billion-dollar bureaucracies (including IARPA) are less good forecasters than less expensive options.

A good article, and the book’s going into my TBR pile.

Comments are closed.