Posts from September 2012 (71)

Each week, we would like to invite readers of Stats Chat to submit nominations for our Stat of the Week competition and be in with the chance to win an iTunes voucher.

Here’s how it works:

• Anyone may add a comment on this post to nominate their Stat of the Week candidate before midday Friday September 28 2012.
• Statistics can be bad, exemplary or fascinating.
• The statistic must be in the NZ media during the period of September 22 – 28 2012 inclusive.
• Quote the statistic, when and where it was published and tell us why it should be our Stat of the Week.

Next Monday at midday we’ll announce the winner of this week’s Stat of the Week competition, and start a new one.

(more…)

If you’d like to comment on or debate any of this week’s Stat of the Week nominations, please do so below!

….and the bartender asks them if they need help setting up for their talks.

The second episode of Nerdnite Auckland is on Tuesday October 2, at Nectar, in Kingsland (if you have trouble finding it, it’s upstairs, above the Kingslander). Presumably it starts at closer to 6:30 this time, since the bugs should have been worked out of the system.

Also, on Wednesday September 26, Cafe Scientifique is on at the Horse and Trap, with Gillian Turner, from Vic Uni Wellington, talking: “Flips and Wiggles — the mystery of Earth’s magnetism”.  They recommend arriving at 6ish for a 6:30 start to the formalities.

From the Stuff story you could be forgiven for thinking heart disease in women is getting worse

Women have overtaken men in dying from heart disease, and the situation is forecast to get worse…

Ministry of Health figures show 5038 women died of cardiovascular disease in 2009, compared with 4712 men, and are projected to increase as the effects of diabetes and obesity worsen.

 Both those statements are true, but the implication is false.  The only thing you can reasonably talk about in health terms (as opposed to economics) is age-specific death rates.  That is, we want to correct for two trends that are not really ‘health’ changes.  The first is population size.  There are more people in New Zealand now than in the past, so there will be more deaths.  The second is age: your chance and my chance of dying of cardiovascular disease next year is higher than it was last year because we’re a year older.  We want to look at rates (fractions) rather than counts, and compare people of the same age.

Age-specific death rates from heart disease are still falling in New Zealand, as they are essentially everywhere in the Western world, and have been for my entire lifetime. That is, a 70-year old woman is less likely to die of heart disease this year than a 70-year old woman was to die of heart disease in, say, 2001, or 1980.

The improvements have been driven by a range of factors including reductions in smoking, introduction of treatments for high blood pressure and high cholesterol, and better heart-attack care. The  fall has been faster in men, who are now catching up to women.   The fall is showing signs of levelling off now for both men and women, and there are reasonable concerns that the trend might reverse in the not-too-distant future.

Since heart disease is a major cause of death for women, and this isn’t as widely appreciated by the public, an increase in targeted health promotion would probably be a good thing.  But that doesn’t mean we should regret the falls in heart disease deaths among men: a better phrasing would be “Men have caught up to women in dying of heart disease, but the situation, for both sexes, is forecast to stop improving.”

There’s a new paper in the journal PLoS One (free access), looking at what research makes the news.

We focused on attention deficit hyperactivity disorder (ADHD). Using Factiva and PubMed databases, we identified 47 scientific publications on ADHD published in the 1990s and soon echoed by 347 newspapers articles. We selected the ten most echoed publications and collected all their relevant subsequent studies until 2011. We checked whether findings reported in each “top 10” publication were consistent with previous and subsequent observations. We also compared the newspaper coverage of the “top 10” publications to that of their related scientific studies.

The media are more likely to report the more surprising findings; these are more likely to be wrong.  The relatively boring research that contradicts these findings doesn’t get reported, because it would put people to sleep.

To a lesser extent the same bias is found in the scientific literature.  If you find something surprising and dramatic, you’re more likely to work nights and weekends to get it written up, and to submit it to a top journal.  Research with methodologic problems is more likely to get past peer review if it’s interesting than if it’s boring.

In the case of clinical trials this publication bias has been recognised as a clear and present danger to patient care, and steps have been introducted to reduce its impact.   More generally it’s hard to see what to do in the scientific literature: we don’t actually want a lot of boring low-quality research in academic journals (we have to read them, after all), and we don’t want to suppress interesting findings because the research wasn’t perfect.

For newspapers, a bit more restraint in  scientific press releases would help.  The philosopher Daniel Dennett had a nice phrasing of this. I don’t remember it exactly, but it was along the lines of “Preliminary scientific results should be treated like any other potentially hazardous laboratory waste and not irresponsibly discharged into the environment”

The Herald tells us that slang and texting are responsible for children not being able to write.

This is one of the topics that Language Log can handle better than StatsChat, so I’ll direct you there for a dismantling of the theory:

• Texting and language skills
• Shattering the illusions of texting

When looking at variation in any sort of proportion, the first step is to work out how much is random variation and how much is systematic and so can perhaps be interpreted or improved.  This is the same principle that makes the ‘margin of error’ important in opinion polls.

In Stuff’s release of the National Standards data there is a ‘Download the data’ link. They have censored a few measurements for privacy reasons, which makes sense.  They have also left out the sample sizes: how many students is each number based on?  For the overall school standards it would be tedious but possible to put this back in by hand using their ‘School Report’ search function, but not for the comparisons broken down by gender and ethnicity.

As an illustration of why this matters, there are multiple schools where 100% of the Maori students are reading at or above the National Standard, and there don’t seem to be any where 100% of all the students are reading at or above standard.  What conclusion would you draw from this about Maori vs Pakeha education in NZ?

The Herald has a pretty good story about the latest migration figures.  It’s nice to see a link to the data source, and there’s some sensible discussion about trends and about the actual implications of a small net outflow of migrants.

Usually when I write about a survey story that gives no details, it’s because the survey is bogus.  Today, Stuff has a story about a genuine survey that says nice things about Kiwis. The World Giving Index has NZ in second place, with a score of 57%, and Stuff says this means “At least 57 per cent of Kiwis give either their money or time to some sort of charity.” 

In fact, the World Giving Index is an average over three questions from the Gallup World Poll, a survey that does face-to-face interviews with a random sample of people from every country in the world (with a few exceptions where it’s not feasible).  The questions are

Have you done any of the following in the past month? 

• „ Donated money to a charity? 
• „ Volunteered your time to an organisation? 
• „ Helped a stranger, or someone you didn’t know who needed help? 

NZ scores 63%, 39%, 69% respectively, so the 57% giving money or time to a charity reported by Stuff is an underestimate.

Otago-born Len Cook was the Director of the Office for National Statistics in the UK from 2000-2005. He also served as Registrar-General of England and Wales and in that role got to decide that Prince Charles and Camilla’s marriage could proceed. Prior to that he spent nearly 30 years at the Department of Statistics in New Zealand, holding the top post of Government Statistician from 1992 to 2000. On Nine to Noon yesterday