Calling all poor soothsayers: cash prizes for good forecasting
As of the 23rd May 2022 this website is archived and will receive no further updates.
understandinguncertainty.org was produced by the Winton programme for the public understanding of risk based in the Statistical Laboratory in the University of Cambridge. The aim was to help improve the way that uncertainty and risk are discussed in society, and show how probability and statistics can be both useful and entertaining.
Many of the animations were produced using Flash and will no longer work.
Do you reckon you have good statistical skills? Now's the chance to prove it in two forecasting competitions that are running this month, both of which feature the Eurovision Song Contest.
The Royal Statistical Society's Crystal Ball competition asks teams to answer 10 questions about events after 28th May, such as the total number of goals in the World Cup, the number of viewers of Eastenders on June 4th, and of course the winning score in the Eurovision Song Contest. The novelty in this competition is that point estimates are insufficient: your uncertainty about your forecast, expressed as a standard deviation, must be given and your final score is decided by a formidably complex formula that should encourage people to honestly express the uncertainty. Top prize £200!. Entries by 28th May, the day before the dreaded Song Contest. One of the questions is self-referencing: you have to guess the number of competition entries.
The other competition is featured on the Kaggle site which hosts forecasting competitions. This one offers a $1000 prize for guessing all the scores given by all the countries in the Song Contest, using absolute error as the closeness criterion. There's also a (more serious) competition for forecasting HIV progression: in both competetions you will have to share your methodology to get the prize.
- david's blog
- Log in to post comments