Monthly Archives: September 2011

On probability, statistics and journalism

heredity and cancer, breast cancer, inherited ...

Image via Wikipedia

This should pose a good teaser for any working reporter and news editor who uses percentages of chance on a day-to-day basis.

If a woman is given a positive screening result after a mammogram, which is bad, what is the probability that she does not have cancer?

Answer: 91 percent.

Why is this? Cambridge University professor David Spiegelhalter explains in the September UK edition of Wired (emphasis is mine):

Mammography correctly classifies around 90 percent of women who go for breast-cancer screening. So when a middle-aged woman is told she has a positive test result, what’s the probability she doesn’t have cancer? The answer, which is surprising to most people, is around 91 per cent. The crucial missing piece of information is the size of her background risk.

So suppose she is from a population in which around one in 100 have breast cancer. Then, out of 100 such women tested, one would have breast cancer and will most likely test positive. But of the 99 who do not have breast cancer, we would still expect around ten to test positive — as the test is only 90 percent accurate. That makes 11 positive tests, only one of which involves cancer, which gives a 10/11 = 91 percent probability that someone who tests positive does not have breast cancer.

Spiegelhalter writes that this is difficult to understand because it is difficult to understand: probability doesn’t make sense, nor follow the rule of logic we think govern our lives and the outcomes of decisions.

But he also correctly identifies a flaw in news reporting where the numerator – the amount of things - is enthusiastically reported, without mentioning the amount of times the event could have happened, the denominator.

So the amount of health scare stories (mentioning no names) that are perpetually reported – invariably from unpublished, unreviewed studies and promoted by PR officers – are lacking in context and thus utterly misleading.  Ben Goldacre has been making this point for years.

Health scare stories may be right to mention that while the relative risk of, for example, getting cancer from drinking/not drinking red wine/eating peanuts/reading the Daily Mail may be increased or decreased. But the absolute risk may be statistically unchanged – when a person is considered as part of a wider population, not just the 1,000 or so that took part in the study.

News naturally focuses on the unlikely and the shocking – it would be boring otherwise. But that doesn’t necessarily mean it has to be misleading.

Enhanced by Zemanta

Thoughts on LinkedIn groups for media brands

This is icon for social networking website. Th...

Image via Wikipedia

LinkedIn has certainly grown in importance for me in the past year since started.

We run a group now running at just under 500 members and it’s been very rewarding to have started some interesting discussions, that have fed into and inspired articles on TMB and hopefully proved useful to people in our community. Here are some entirely unscientific thoughts based on what I’ve learned and also what I see from other groups from media brands:

  • Saying ‘what do you think?’ isn’t always enough to get a discussion going. Often people will say to themselves “er, I don’t think anything” and move on to answering emails. If you ask a  specific questions, it might result in some specific answers. Rory asked people what advice they’d give a younger version of themselves – the title of an article he did for the site – and 25 comments later the thread is still going (my favourite tip: “Go into investment banking”).
  • Shovelware can be useful, but not always. We added the LinkedIn sharing buttons to every page on TheMediaBriefing, which is a good way for readers to add a story to their professional network. Some posts are shared more than 20 times, which for a professional B2B brand like TMB means our articles are being seen by 100s of senior media people – our core target audience. Increasingly, LinkedIn is being used a content discovery platform. But, adding a link to the group using the button only starts a discussion - it doesn’t develop it. Plus, the automated way LinkedIn’s API presents button-fed links looks automated and a bit inhuman. It doesn’t look like part of a lively community.
  • Posts with more comments get more comments: the first thing people see when they log in to the group are the “Most popular”, “Latest updates” and “Managers’ choice”. As with news articles, people drop into the discussions with lots of comments and are far more likely to add their thoughts when people (particularly people they know) have already said something. Not many people like to be the first to say something.
  • Be tough but fair on self-promoters: It’s only a matter of time after starting a LinkedIn group before someone posts a link promoting their site or product. We even get people linking to their own discussions elsewhere. There’s an easy way to deal with this: “Mark as promotion”. This takes the link into the promotions section and out of the main discussion list. I’m more than happy for people to start a thread on something and link to themselves if appropriate (TMB likes linking in a big way, of course), but it has to be a discussion, not just a link-dumping, traffic-boosting exercise. Some marketers do this on an automated basis, incidentally.
I’d be very interested to hear any tips or advice anyone else has, or links to guides that are worth reading.
Enhanced by Zemanta