Understanding Uncertainty (original) (raw)
Medicine, poison, poison, poison, ……
Submitted by david on Sat, 09/01/2016 - 11:55am
Yesterday the Chief Medical Officer announced new guidelines for alcohol consumption. The Summary says,
The proposed guidelines and the expert group report that underpins them, have been developed on the basis of the following principles:
Speed cameras, regression-to-the-mean, and the Daily Mail (again)
Submitted by david on Fri, 07/06/2013 - 10:55am
It was interesting to hear ‘regression-to-the-mean’ being discussed on the Today programme this morning, even if the quality of the debate wasn’t great. The issue was the effectiveness of speed cameras, which tend to get installed after a spate of accidents. Since bad luck does not last, accidents tend to fall after such a ‘blip’, and this fall is generally attributed to the speed camera, whereas it would have happened anyway: this is what is meant by ‘regression-to-the-mean’.
Alcohol in pregnancy and IQ of children
Submitted by david on Fri, 16/11/2012 - 5:54pm
Some of the coverage of yesterday's story about drinking in pregnancy and IQ of children was not entirely accurate. The Times reported that 'women who drink even a couple of glasses of wine a week during pregnancy are risking a two-point drop in their child's IQ', and 'children whose mothers drank between 1 and 6 units a week - up to three large glasses of wine - had IQs about two points lower '(than mothers who did not drink).
Data overload?
The government announced last week that it would be greatly expanding the amount of data which it shares with the rest of us. Its white paper spells out the detailed principles of the new approach, and there is much in it to commend. It addresses many of the hideous features of government data at the moment, such as departments' habit of publishing in proprietary formats (usually Excel); the fact that data cannot necessarily be re-used without obtaining explicit permission; and the lack of coherence between different datasets on essentially the same topic.
Drinking again
Submitted by david on Fri, 01/06/2012 - 8:13am
Alcohol can cause very serious problems, both for individuals, their families and society. But the Daily Mail’s story yesterday with the headline “Don't drink more than THREE glasses of wine a week: Oxford study claims slashing the official alcohol limit would save 4,500 lives a year” almost universally aroused derision among its many commenters.
The dangers of 'don't worry'
Submitted by david on Tue, 27/09/2011 - 7:48am
(appeared in the Times, 26th September 2011) - pdf here
Now that the rogue US satellite has crashed into the Pacific we can all come out from under our beds. The biggest bit of the satellite was about the weight of an adult gorilla, although not as soft, and travelled at 100 mph so it sounds rather ominous, but people only take up one 80,000th of the earth’s surface so it would be more than an unlucky day if anyone had been hit. 40 tons of debris got scattered over mainland USA after the Columbia shuttle disaster and nobody was injured, although NASA afterwards concluded there had been around a 1 in 4 chance of some casualties.
Lottery league tables
Submitted by david on Thu, 15/09/2011 - 11:13am
The Daily Mail and other media sources have featured league tables for the 'luckiest parts of the country' based on the proportion of the population that have become millionaires by winning the lottery. Straight Statistics have done a nice demolition job on this absurd story, pointing out that any comparison should be based on the number of tickets sold, not the population.
Visualising uncertainty
Submitted by david on Thu, 15/09/2011 - 9:54am
We have had a review paper published in Science called Visualising uncertainty about the future, although it primarily focuses on probability forecasts.
You may access the full paper by following the links below.
Spotting a hoax using statistics
Submitted by david on Wed, 03/08/2011 - 6:10pm
A report claiming that users of the Internet Explorer browser had lower IQs than users of other browsers has been revealed to be a hoax. I had been asked to comment on the report by BBC Technology and had got suspicious about the figures. The perpetrators of the hoax, which had received extensive coverage, have listed the reasons why they should have been detected, but did not include 'dubious statistics' in their list.
Another Look at Entropy
Entropy is a term that draws both fear and reverence from the greatest physicists and mathematicians. How do you describe it? What does it even mean? Who in their right mind would want to quantify a phantom concept that's impossible to see or touch?
Spinning mobile phones
Submitted by kevin on Mon, 06/06/2011 - 2:10pm
When it comes to causing cancer in humans, is using a mobile phone as risky as talcum powder, or as risky as coffee, or as risky as the notorious insecticide DDT? Actually we don't know, as I explained in my previous blog entry on last week's IARC announcement on mobile phones and brain cancer. That didn't stop the media comparing the risk of mobile phone use with all these things and more. But why did different newspapers make different comparisons?
Thinking, but not about uncertainty
Submitted by kevin on Thu, 24/03/2011 - 11:47am
Google seems to be doing pretty well everything these days. Their UK operation has just published the first issue of a new magazine, Think Quarterly, and it's all about data. It looks very pleasant, particularly if you read the version that emulates a print magazine. And there's some interesting content, including interviews with Hans Rosling and with Hal Varian, Google's Chief Economist who famously said in 2009 that "the sexy job in the next 10 years will be statisticians." But, strangely, the whole magazine says nothing explicit about uncertainty.
Data: can we cope?
Submitted by kevin on Tue, 15/02/2011 - 1:30pm
Are we all drowning in a deluge of data? Are our data tools and systems managing to keep up with all the numbers we're collecting all the time? A series of articles in the journal Science doesn't give an entirely positive view, at least in terms of what's going on in the scientific research community. But what does that have to do with uncertainty?
The message in ley lines
Submitted by kevin on Wed, 26/01/2011 - 1:18pm
Tom Scott has a marvellous web page, click here, that lets you check whether the place you live is on an ancient mystical energy highway. At least, it does if you live in England. If not, you can try one of the example postcodes he gives, or indeed the postcode of UU HQ here in Cambridge, CB3 0WB. Just don't forget to check the important warning that Tom gives after you've got your results.
Nice probability puzzle
Submitted by david on Mon, 13/12/2010 - 8:44am
For the last few weeks, Chris Maslanka's excellent maths puzzle column in the Guardian has been running variants on the following problem. Fred and Sam play a game in which the winner is the first to flip a head. They take it in turns, Fred starting. What's the chance that Fred wins? I have been asking this to 6th form audiences and the general response is 2/3 or 3/4, but nobody can say why. Here is the solution I have been using.
A sad day for molluscs
Submitted by david on Tue, 26/10/2010 - 6:46pm
We are sorry to hear that Paul the ‘psychic’ octopus has died. Who would have predicted it? Most people, in fact, since an octopus is only expected to live 2 years. Fortunately a documentary film team got to Paul before his demise and conducted in-depth interviews. They also filmed me doing an explanation of the maths behind Paul – this will probably be cut but at least we now have an article about him!
Hang out the flags!
Submitted by david on Wed, 20/10/2010 - 10:14am
The great day has arrived. The first UN World Statistics Day, that is, which naturally falls on 20.10.2010. The bunting is out, and statisticians everywhere will emerge from their data-mines, blinking through their pebble spectacles. They will throw off their drab grey suits and dance in the street, discard the row of pens in their top pocket and trim their unruly hair, their dull monotone will turn to song and they will stop staring at their shoes.
Paul - the soothsaying cephalopod
Submitted by david on Fri, 09/07/2010 - 3:26pm
Article in today's Times included below. I should have included the important observation that even if Paul's final two predictions are correct, it does not change my total belief that he is not psychic and the results are just chance. Essentially when a hypothesis has zero initial probability, no amount of surprising evidence will shift that belief. Oh dear, what a closed-minded person I am.
The risks of war and peace
Submitted by david on Fri, 11/06/2010 - 1:42pm
Who is exposed to the greater lethal risk: a member of the UK forces serving in Afghanistan, or an average patient spending the night in an English hospital? Of course the question can’t be answered exactly: it all depends on who we mean and how we measure risk. But statistics can give us a ball-park figure that may be surprising.
The risks of Eggstasy
Submitted by david on Thu, 04/02/2010 - 4:43pm
There has been extensive coverage of a box of 6 eggs found to be all double-yoked:an event that was given odds of a trillion to 1 against. This was based on the British Egg Information Service saying 0.1% ( 1 in 1000) eggs were double-yoked, and so getting six of these required these odds to be multiplied 6 times. In fact this gives 1 in 1,000,000,000,000,000,000, but which was reported as a trillion (now usually taken as 1,000,000,000,000).
The Daily Mail did a good demolition of this story, and it is a good example of what can go wrong when people try and work out chances.
Can you rank hospitals like football teams?
Submitted by david on Sun, 06/12/2009 - 4:16pm
Elsewhere on this site we talk about the difficulties in making reliable rankings of footbal teams, but at least people can agree that winning matches is a reasonable way to measure the quality of a team. Hospitals are different - even something 'obvious' such as mortality statistics may not be the best way to asses patient safety. This is an article that appeared in the Times on December 2nd, with suitable links added.