October 16, 2007
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.
Priorities Meeting Oct.16th , 2007
David made mention of the More or Less Radio Program and invite to talk about league tables. We will be pursuing this.
A: David will contact and get details.
We will need to give links at some point to show off the Drupal website to specific individuals.
Definite push to get league tables sorted. R briefly mentioned as something to become familiar with.
David explained the random league table process in relation to football leagues and how at the end of the season, we would like to be able to know the true rank of the team. It is also good for trying to determine how many points the team is expected to get in the next game. David demonstrated a graphic that shows the retrospective results once calculated. So there are 4 steps to demonstrating this process, where we would go from B to D with calculations:
A) Simulated random league
B) Estimate quantities/measures of qualities (these have to be allowed to go up and have to be dynamic)
C) Simulated future league, ie. A real prediction
D) A statement of true ranking
We have to find a way to map from a single number what the probabilities are. Right now the 0, 1, 3 goals possible don’t allow for it directly.
A: Find easily nickable data for football info. Steve Brooks and other contacts.
A: DS to develop specs on the above process.
It will be the same program for football season ranking. Compare a fake (random) table to a real table, with range increasing, where you see the actual spread and can start calculating skill. The next level up is to calculate distribution over the maximum.
The interesting part of cataloguing league tables for our purposes is that they are both an issue and a method.
A: DS will look at how to use this graphic for other issues. Eg. Health, economic issues.
A: Arciris and/or DS need to look at possibilities section of RSS feed so that we can sort it out on delicious, maybe with a yahoo pipe.
A point was made that the lottery might be the way to lead into other parts of the website, using the animations to move into differing levels. We are to target getting the lottery page completed.
For the homepage, we can go with a news or magazine style format. The news format has the advantage that we don’t have to do monthly etc. updates. The RSS feed will enable this. Can pull out of the RSS to put into topics or presentations/blogs.
We had a small blog discussion. We will not be a big part of project but once have feeds running as we want them, it will be an efficient process to update through blogs and divert people to links.
A: Hauke might do a presentation of the Programme in Liverpool, Nov.7th if DS not available.
Meeting adjourned.
