Stats Chat

A new Australian website with information for journalists about good science journalism

The bulk of journalists entering undergraduate and postgraduate courses in journalism come from an arts and humanities background and can find reporting complex science stories a challenge.

To address this challenge, an expert working group—comprised of some of Australia’s top science journalists and science communicators—published a report in 2011 with recommendations to support journalists who report science. 

One of the recommendations in the report—Science and the media: From ideas to action—was to “Develop a unit on reporting research that can be incorporated into undergraduate journalism courses“.

The group felt that the accuracy of reporting on key science issues could be improved if journalists are given some basic training in reporting on research findings during their undergraduate degree. This could include training on how to assess the credibility of experts, understanding the peer review process and making sense of scientific reports and basic statistics. This training is applicable across a wide spectrum of news stories and would be beneficial for all journalists not just those wanting to work on a science round.

They currently have six modules:

• Module 1 – Telling an engaging science story
• Module 2 – Understanding a research paper
• Module 3 – Understanding statistics and numbers
• Module 4 – Reporting politicised science
• Module 5 – Using social media for news
• Module 6 – Visualisation in science journalism

(via the NZ Science Media Centre)

From Stuff

The [product being advertised] survey, which involved 2034 participants, found that 11 per cent of drivers admitted to having sex while driving. Men were three times more likely to admit to participating in sexual activity than women .

Firstly, a little skepticism would be appropriate here.  Isn’t it just possible there’s something wrong with the survey? If you go and search for the press release, you find

This online survey is not based on a probability sample and therefore no estimate of theoretical sampling error can be calculated.

which is not encouraging. Also, the breakdown by age in the press release says the proportion who have ‘participated in sexual activity’ while driving is even higher, 17%, among 18-44 year olds. And flirting with a driver in a different car is apparently less common than having it off with a passenger in the same car.

I suppose I could just have led a very sheltered life. But if these figures are accurate you’d expect the AA to have noticed and to have a slightly different list of the top ten driving distractions. And surely it would be hard to have missed the salacious headlines whenever one of these couples caused an accident, which 5% of them report having done.

I’m not sure if it’s encouraging or discouraging that this is a  Fairfax story, not something from the Daily Mail.

From a UK real estate ‘insight’ paper, via Twitter, the age distribution of London immigration and emigration

As a technical quibble, this is the sort of graph that shouldn’t be in JPEG format. It should be in PNG or GIF — you can easily the see artifacts produced by JPEG compression.

From Felix Salmon at Reuters

Let’s say that you saw various news reports about an event, and that different words were used to describe the weather: some said it was “cold”, others “brisk”, others “frosty”, others “wintry”, and so on. You wouldn’t raise an eyebrow: you’d see that they were all describing the same thing, in slightly different language, and you wouldn’t demand an explanation for the “discrepancy”. Well, numbers in news articles behave like words: they’re trying to describe the state of the world. That’s why the NYT has banned the use of “record” or “largest” unless inflation is taken into account. What matters is not the mathematical relationship between abstract numbers, but rather the state of the world that is being described.

Go and read the whole thing.

Remember the shootings at Sandy Hook elementary school in Newtown, Connecticut last December?

Since then, Slate magazine has been collecting news reports of gun deaths in the US. Here’s a map.

Actually, that’s a map of just the 1000 locations with the most deaths.

As of today, they have 10,001 deaths with the place and the name of victim known. That’s going to be an underestimate, since some don’t make the news. And since the number doesn’t include suicides, who make up about 60% of gun deaths in the US according to the CDC.  These mostly aren’t mass shootings, so they don’t attract international attention, but there are about as many gun deaths as car deaths in the US.

It’s not simply a matter of number of guns: the US has about 3.5 times the number of guns per capita as New Zealand, but about seven times the gun death rate per capita (nearly ten times the rate if you don’t include suicides).  It may be more that for a lot of people in the US, an important reason to own a gun is so that you would be able shoot another person with it if the circumstances arose. In a recent survey by Pew Research, 48% of gun owners gave self-protection as their main reason for owning a gun, and 79% said owning a gun made them feel safer. I can’t find figures for NZ, but I’d expect hunting and target shooting to be more common reasons here.

A number that should be in all stories about accidents on special days of the year: 4500.  That’s roughly how many new claims ACC gets per day: divide the 1.7 million per year by 365.

The Herald passes on the ACC’s figures of 31 Halloween-related injuries and 840 attributed to Guy Fawkes. First you have to divide by five, since these are aggregate totals over five years. Then divide by the average number of claims per day to find that Guy Fawkes Day is responsible for about 4% of a typical day’s injuries, and Halloween racks up about 0.1% of a day.

It wouldn’t be surprising if Halloween actually prevented more injuries than it causes — participating children will be doing something safe under adult supervision, rather than teasing innocent pets, fighting with siblings, getting underfoot in the kitchen, or participating in team sports.

The Herald tells us

Most women are more scared of public speaking than they are of death, it has been revealed.

Researchers who polled 2,000 women found many are far more at ease with meeting their maker than they are of standing in a room talking to an audience hanging on their every word

On the other hand experience in  teaching suggests that a fairly large fraction of women would, given the choice, prefer public speaking to failing a university course.  

Since this is a survey commissioned by a London tourist attraction, and they aren’t providing any information about the survey methods, it’s hard to tell why the results are the way they are. All we can really tell is that it’s the sort of research where asking if the results are true is missing the point.

• The Legatum Prosperity Index ranks countries on a range of domains including economy, health, governance, social capital.  In their 2013 report NZ comes in 5th, and the top country in the Asia/Pacific.   Apparently, about a quarter of Kiwis believe there is widespread business or government corruption, and this is less than the figure almost everywhere else (Denmark is the exception)
• A post on risk communication in the recent UK storm, from Ross Anderson, a computer security expert.
• I have heard people comparing the UK storm to the recent Wellington storm, which didn’t cause any deaths despite stronger winds. Note that the UK storm killed roughly  one in twenty million of the UK population. In Wellington the same mortality rate would be about 0.01 people.
• The Herald tells us “Texting, reading magazines, eating and applying makeup are among the top 10 driver distractions, an AA Insurance survey has found.”  Looking at the press release, AA asked about twelve distractions. Eleven of them ended up in the top ten, so the list can’t be very sensitive to respondent opinion. 

From NPR News, a story on the rise of electric bikes. With some unfortunate graphs.

Or, on the same axes

From “Great Schools”, a US website with information about schools, via wtfviz.net