Skip to main content

Science, girls, statistics - what could go wrong?

The use of statistics by the media is something that constantly drives me round the bend. (At least, it does 90% of the time.) Now the BBC has wound me up by combining science, gender issues and, yes, statistics.

To be fair these are not blatant errors, but rather that hoary old standard, not being scrupulous about separating correlation and causality. As we saw with the infamous high heels and schizophrenia study, even academics can be prone to this, but the media does it every day. One very common example is where they tell us on the news that the stock market went up or down as a result of some event. Rubbish. In most circumstances the stock market is far too chaotic a system to attribute a change to an event that happened around the same time. It's guesswork and worthless.

Here, the misuse is slightly more subtle. 'Girls who take certain skills-based science and technology qualifications outperform boys in the UK, suggest figures' says the relatively mild headline. But is this really what the figures say, and if so what should we deduce?

According to exam publisher Pearson, girls who take BTECs in science and technology are more likely than boys to get top grades. Now here's a key sentence. According to the BBC 'Despite this success, girls are vastly outnumbered by boys on these courses.' The implication here is that this is just the tip of the iceberg, and with many more girls we would have lots of better grades. The suggested correlation is of gender with good grades. However it could equally well be that this is self-selection, a regular plague on the houses of those attempting to interpret statistics. If there are large numbers of boys on the courses, many of them could be there because 'that's what boys do' not because they have any talent for the subject. By contrast, if there are a small number of girls (in this case between 5 and 38% depending on topic), then they are likely at the very least to have greater than average enthusiasm, and quite possibly greater talent. If this is the case, all this is saying is that 'better than average female candidates do well compared with average male candidates.' Not quite such a strong story - in fact not a story at all.

The article then goes on to quote someone saying too few girls take STEM subjects. Now, I think this is true. We still have an artificial cultural bias about girls going in for science and it is wrong. However, what we mustn't do is to try to support the belief that this is wrong with data that doesn't contribute anything to the argument. By putting the 'girls are better at it' supposed statistic alongside the desire to have more girls in the subject implies that there is something inherent in the gender that makes girls better at it, so we want more of them. No, no, no. We want more because girls should have the same opportunities, because they shouldn't be put off science/tech because their peers think it's inappropriate. Not because a dubious interpretation of stats implies we could improve the quality of our STEM stock of students because girls are better at it. Without effective evidence this is just as sexist as saying girls shouldn't do science because it's too difficult for their little brains.

A girl and a science building. See, they can go together! *
One last example from the article. We have a quote from Helen Wollaston of Women into Science and Engineering saying the results prove "that girls can do science, IT and engineering." That's a silly thing to say. Firstly there is nothing to prove. Why would they not be able to? But also, as we've seen, all these results seem to show is that the most motivated girls are better than the average boys. There should be no need to use dubious statistics to 'prove' that girls can do STEM. I don't think anyone has doubted this since we stopped thinking (as they genuinely once did) that these subjects would overheat delicate female brains. What we need to prove is that far more girls can be interested in STEM and that we can change the culture so that it is cool for them to do so. That is a totally different issue - but it is the real one we face.

* In the interest of openness and scientific honesty, I ought to point out that the woman portrayed was a music student.


Popular posts from this blog

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

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

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