Skip to main content

Statistics can be true but misleading - shock, horror, alcohol is bad for you

Headlines on the BBC News tell us starkly (if somewhat smugly) 'No alcohol safe to drink, global study confirms.' But like all statistically-based stories, the devil is in the detail.

First port of call in any such situation is David Spiegelhalter, the Winton Professor of Public Understanding of Risk at Cambridge. And the story, according to him, is rather different from the scare headlines. He starts by pointing out a bizarre omission in the paper quoted - they only show relative risk, not absolute risk.

The trouble with relative risk is that it is often hugely misleading. Imagine the headline 'Murder rate in city increases by 100%'. Wow - that city appears to have hit the ropes, big time. However, that is a relative statistic. We don't know what that 100% represents. Exactly the same data could also be represented by the headline 'One murder last year, two murders this year.' That is a 100% increase. But far less scary sounding. So the paper's authors should be reprimanded. Luckily, though, apparently the press office, often the villains in misrepresentations of papers, actually published the real numbers - which to the BBC's credit, they do use, rather than just the relative values.

And what do those real numbers say? Four people in 100,000 who had around 1.25 units of alcohol a day would develop a related health problem or sustain an alcohol related injury in one year (it's hard to imagine how 1.25 units could be shown to cause an injury, but we'll overlook that). That's a low number. All activities have risks attached (getting out of bed, crossing the road, going in a car...). And that's not even considering relatively high risk activities. Life involves risk. The mere existence of risk is not in itself a reason not to do something - there's always a cost/benefit tradeoff, and many people who drink relatively small amounts get considerable pleasure from it.

This is why it's worrying that the paper goes on to say that their findings suggest public health bodies should consider recommending total abstention. The significant problem here is not light drinkers, but heavy drinkers, where the risks start to go up in a big way.

Something the BBC doesn't cover is Spiegelhalter's other key point, which is also interesting. He notes that this study seems to contradict earlier research which showed that those who abstained from drinking alcohol had a significantly higher (20%*) death rate than moderate drinkers. I have already seen this used elsewhere in an attempt to debunk the science - but that's the wrong message to take away. This higher death rate was from all causes, not just specific alcohol-related causes. And as Spiegelhalter points out, the kind of people who are advised by their doctors not to drink any alcohol tend to be those who have serious medical problems. It's not the lack of alcohol that kills them, it's those problems.

So, media people - please be careful how you use statistics. It's fine to report studies like this. But don't - as the BBC did - put just part of the essential explanation right down at the bottom and make it sound like a minor quibble, rather than something that goes against your shock headline and the tenor of the vast majority of the article.

* Yes, I know this is a relative statistic, but this is the kind of circumstance where they are useful. 

Comments

Popular posts from this blog

Is 5x3 the same as 3x5?

The Internet has gone mildly bonkers over a child in America who was marked down in a test because when asked to work out 5x3 by repeated addition he/she used 5+5+5 instead of 3+3+3+3+3. Those who support the teacher say that 5x3 means 'five lots of 3' where the complainants say that 'times' is commutative (reversible) so the distinction is meaningless as 5x3 and 3x5 are indistinguishable. It's certainly true that not all mathematical operations are commutative. I think we are all comfortable that 5-3 is not the same as 3-5.  However. This not true of multiplication (of numbers). And so if there is to be any distinction, it has to be in the use of English to interpret the 'x' sign. Unfortunately, even here there is no logical way of coming up with a definitive answer. I suspect most primary school teachers would expands 'times' as 'lots of' as mentioned above. So we get 5 x 3 as '5 lots of 3'. Unfortunately that only wor

Why I hate opera

If I'm honest, the title of this post is an exaggeration to make a point. I don't really hate opera. There are a couple of operas - notably Monteverdi's Incoranazione di Poppea and Purcell's Dido & Aeneas - that I quite like. But what I do find truly sickening is the reverence with which opera is treated, as if it were some particularly great art form. Nowhere was this more obvious than in ITV's recent gut-wrenchingly awful series Pop Star to Opera Star , where the likes of Alan Tichmarsh treated the real opera singers as if they were fragile pieces on Antiques Roadshow, and the music as if it were a gift of the gods. In my opinion - and I know not everyone agrees - opera is: Mediocre music Melodramatic plots Amateurishly hammy acting A forced and unpleasant singing style Ridiculously over-supported by public funds I won't even bother to go into any detail on the plots and the acting - this is just self-evident. But the other aspects need some ex

Which idiot came up with percentage-based gradient signs

Rant warning: the contents of this post could sound like something produced by UKIP. I wish to make it clear that I do not in any way support or endorse that political party. In fact it gives me the creeps. Once upon a time, the signs for a steep hill on British roads displayed the gradient in a simple, easy-to-understand form. If the hill went up, say, one yard for every three yards forward it said '1 in 3'. Then some bureaucrat came along and decided that it would be a good idea to state the slope as a percentage. So now the sign for (say) a 1 in 10 slope says 10% (I think). That 'I think' is because the percentage-based slope is so unnatural. There are two ways we conventionally measure slopes. Either on X/Y coordiates (as in 1 in 4) or using degrees - say at a 15° angle. We don't measure them in percentages. It's easy to visualize a 1 in 3 slope, or a 30 degree angle. Much less obvious what a 33.333 recurring percent slope is. And what's a 100% slope