Stats Chat

Q: The Herald says  “Bacon makes everything better – research“. What research is this?

A: Wired magazine and the Food Network did a simple analysis of recipe ratings, comparing recipes for roughly the same thing with and without bacon (and a similar analysis for some other ingredients). For example, they compared sandwiches with bacon to sandwiches without bacon.

Q: And did bacon make everything better, like the headline says?

A: No.

Q: Ok, did it make nearly everything better?

A: No.

Q: Lots of things?

A: Yes. Though not necessarily by very much. Here’s the results. The biggest improvement is about 0.2 points on a 5-point scale.

Q: Are there actual numbers given somewhere, or results of other comparisons of ingredients?

A: No.

Q: These eight groups look a bit strange: kale vs all pasta dishes, for example. Did they look at other groups?

A: They might well have, but they aren’t telling.

Q: Do they explain why bacon is so good?

A: The Herald has an explanation (in fact, they have it twice, so it must be good). It’s the Maillard reaction

Q: Is that something that’s unique about bacon, which would explain why it’s different from other ingredients.

A: No. It’s in a huge range of foods.

Q: Is this sort of thing the future of data journalism?

A: Well, Wired says “Food is so personal and subjective that we’re always talking about it in vague and imprecise ways. But one of the many amazing things you can do with big-ish data is give precise questions to answers that always seemed so subjective.”

Q: Is that as bogus as it sounds?

A: Yes. For example, this is a sample where the average kale dish is rated  more highly than the average dessert. Generalisable and objective food preference ratings are not what we’re looking at.

Q: Does this story, perhaps, come from the Daily Mail?

A: Why, yes. Complete with the misspelling of sriracha.

• Scott and scurvy.  James Lind showed that citrus juice would cure scurvy, in the first controlled clinical trial, but the knowledge had been lost by the time of the Scott Antarctic Expedition. Interesting on history and on how facts depend on concepts.
• Inside 23andme: about personal genomics.
• Data are the new drugs: from Nautil.us, also about personal genomics

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 November 1 2013.
• Statistics can be bad, exemplary or fascinating.
• The statistic must be in the NZ media during the period of October 26 – November 1 2013 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…)

Everyone knows that areas with more fast-food stores have more overweight people, and it certainly makes sense that fast food is bad for you. Like almost everything else, though, it gets more complicated when you start looking carefully.

Firstly, earlier this year Eric Crampton wrote in NBR about some research by an economics PhD student, Rachel Webb, who was trying to take advantage of this well-known relationship to unpick some aspects of correlation vs causation in the relationship between mother’s weight and infant’s birthweight. She found that, actually, areas in New Zealand with more fast-food outlets didn’t have more obesity to any useful and consistent extent.

Secondly, there’s new research on diet and fast food using data from the big NHANES surveys in the USA.  It confirms, as you might expect, that people who eat more fast food also eat less healthily at other times.

In 2006, statistics celebrity Hans Rosling asked students at the Karolinska Insitute about international child mortality. In each of the following pairs of countries (presented in alphabetical order within pairs), which one has higher child mortality?

• Sri Lanka or Turkey?
• Poland or South Korea?
• Malaysia or Russia?
• Pakistan or Vietnam?
• South Africa or Thailand

None of these are close — they differ by at least a factor of two — but the students did significantly worse than chance, averaging less than two correct answers out of five.

Gapminder.org has a new ‘Ignorance Project’ aiming to find out what important facts about global health and welfare are widely misunderstood.  They don’t just have a naive ‘information deficiency’ view of this ignorance:

When we encounter ignorance, we want to find a cure. Sometimes the facts just have to be delivered. But in many cases, the facts are little known as they don’t fit with other misunderstandings, they are counterintuitive, such as the most of the outdated concepts about the world population. In these cases we need to invent a new simple way to explain it. Those new explanations are the essence of Gapminder’s new free teaching material that make it fun and easy to teach and to learn a fact-based worldview.

It may not work, but it’s worth a try

(more…)

From Stuff, under the headline ‘One in 10 Kiwis now alcoholic‘

One in 10 New Zealanders could now be considered “alcoholic” according to new diagnostic criteria – but the majority of those with a drinking problem are unlikely to recognise it because the issue is so common.

The new estimate of 400,000 “alcoholics” in New Zealand – around 10 per cent of our 4.4 million population – was tallied up by Professor Doug Sellman from the National Addiction Centre at the University of Otago.

It is significantly higher than the Ministry of Health’s 2006 estimate which says 3 to 6 per cent of the population has an alcohol issue.

Sellman’s figures are based on the new diagnostic criteria for “alcohol use disorder” recently published in the fifth edition of the Diagnostic and Statistical Manual (DSM) of the American Psychiatric Association.

From the president of the American Society for Addiction Medicine, in a review of DSM-V

DSM-5 has “Alcohol Use Disorder,” which comes in mild, moderate and severe flavors, suggesting the inadequate pyramid approach. There are 11 possible symptoms of the “use disorder,” of which two are necessary to achieve a mild specifier, four for moderate and six for severe. “Alcohol use disorder is defined by a cluster of behavioral and physical symptoms,” the authors of DSM-5 state. I have no problem with that except that some may confuse “alcohol use disorder” with addictive disease or with alcoholism

Some may, indeed.

Via Keith Humphreys, being arrested is a very common experience for young people in America: using the National Longitudinal Survey of Youth, Richard Braeme and colleagues found

By age 18, the in-sample cumulative arrest prevalence rate lies between 15.9% and 26.8%; at age 23, it lies between 25.3% and 41.4%. These bounds make no assumptions at all about missing cases. If we assume that the missing cases are at least as likely to have been arrested as the observed cases, the in-sample age-23 prevalence rate must lie between 30.2% and 41.4%. The greatest growth in the cumulative prevalence of arrest occurs during late adolescence and the period of early or emerging adulthood

• The long list from the 2013 Information is Beautiful awards. Some are beautiful; some are only beautiful; but many are interesting.
• Some people will be prosecuted for not filling in census forms, but only on the order of 1% of those who didn’t.  That’s about the same as the proportion of pot smokers who get caught and prosecuted.
• Despite all the talk about Auckland’s house prices, there’s plenty of room for things to get worse. Median house prices in Sydney just passed A$700000, well over NZ$800000.
• ‘Chasing the noise’ in quality improvement, from Andrew Gelman
• From journalism blog ‘Heads Up’: As a general rule, if you take newspaper headlines about survey results at face value, you should stay away from those friendly games of chance at the county fair.

I’m in Sydney at the moment, so this is topical, as well as being an illustration of maps, infographics, and internet fact-checking.

From Paul Rosenzweig on Twitter, allegedly a map of the bushfires shown on NBC News in the US

People in Australia think this map is hilarious/outrageous depending on personality — the current emergency was just in New South Wales.  That was my reaction too. But the NBC News blog gets this right, which is a bit confusing

However, @Aus_ScienceWeek, the people who run National Science Week, point out that the map looks rather like the appropriate subsection of NASA’s satellite-based fire map from mid-September

so it might well be correct in the sense that there actually fires in those places, though still wrong as a description of the emergency.

Team Ratings for the ITM Cup Finals

Here are the team ratings prior to the ITM Cup Finals, along with the ratings at the start of the season. I have created a brief description of the method I use for predicting rugby games. Go to my Department home page to see this.

Here are the team ratings prior to this week’s games, along with the ratings at the start of the season.

Performance So Far

There is a problem with the code I have been using for assessing performance, due to the unusual schedule in the ITM Cup, where some teams play more than one game in a week. I haven’t had time to alter the code so am omitting this section for the time being. Look at last week’s post to see how the predictions went. For the record, there were 3 games correct, out of 4 games played last week

Predictions for the ITM Cup Finals

Here are the predictions for the ITM Cup Finals. The prediction is my estimated expected points difference with a positive margin being a win to the home team, and a negative margin a win to the away team.