Posts tagged Winner (58)

Thanks to Graeme Edgeler for winning our latest Stat of the Week competition and for his excellent explanation:

Statistic: “Māori adults have the highest levels of trust in the police, the health system & the courts. The lowest in the media”

Source: Tweet from Stats NZ

The statistic is written in a way that suggests Māori adults have the highest level of trust in the police etc., that is higher levels of trust than anyone else has in the police.

What the report actually shows is that the police etc. are the institutions in which Māori adults place the most trust as among institutions. It says nothing about whether Māori adults have more trust in them than anyone else. Anyone reading the tweet would think they did, but that was not even assessed.

It should be stat of the week, because, even if its not the most egregious stat this week, that fact that it is from Statistics New Zealand makes it worse.

Congratulations Graeme!

Thanks for your nominations last week for our Stat of the Week competition!

This week, we’ve chosen the following to be our winner:

“‘Rates of participants brushing their teeth rose from 53 per cent to 73 per cent during the trial.’

This story got quite a bit of coverage, the stat actually relates to an increase in the number of people texting and saying they had brushed their teeth (far from the same thing).

The Herald got the context correct in their coverage:

This still seems to just be evidence that people will say anything when nagged enough.”

Congratulations Ben Moore!

Thank you for your nominations in last week’s Stat of the Week competition.

We’ve chosen Nick Iversen’s nomination of the NZ Herald article about elephants facing extinction:

The article claims that 100 elephants are killed every day and that elephants will be extinct by 2025.

Over 11 years 100 per day means 400,000 elephants will be killed. I can think of many reasons why this doesn’t mean that elephants will become extinct.

1) the killing rate will drop as elephants become more scarce

2) there will always be protected populations that aren’t subject to the killing

3) elephants are giving birth to new elephants

According to the Wikipedia page on elephants an estimate is that there were 440,000 elephants in 2012. So now we know how the author of the article did the calculations – divided 400,000 by 100 elephants a day.

So let’s keep using Wikipedia numbers and see what we find. “…populations in eastern and southern Africa were increasing by an average annual rate of 4.0%.” Well there you go. Even with culls of 100 a day the population is still growing. So no extinction.

Let’s assume that the 4% is BEFORE the culling. That’s adding 17,600 animals each year and the cull is removing 100 a day so that extends the population out for 21 years. This won’t happen due to points 1 and 2 above.

Note that the 4% figure doesn’t apply to all populations. But my point is still valid. If some populations are increasing in size there will be no extinction.

Thanks Nick for the great explanation!

Thanks to James Green for nominating this fascinating statistic (if true):

“A 1 per cent improvement in broadband connectivity is estimated to cause a drop of 200 million litres a year in national fuel demand”

The NZ Herald quoted this (without attribution) but Thomas Lumley tracked down the source of the statistic to a report by Z Energy. The report contains no further details on the statistic.

James wrote:

“Would be fascinating if true, but without them revealing an actual source, seems difficult and barely credible to firmly link these two.”

Congratulations James for being our Stat of the Week Winner!

Hope you all had a wonderful summer! Thank you to everyone who nominated stats in the media during the summer break period. We’ve chosen Tommy Honey’s nomination to win the prize:

Statistic: Food in Guinea, Gambia, Chad and Iran costs people 2 times more than other consumer goods, making those the most expensive countries for citizens to buy food

Source: NZ Herald
Date: 20 January 2014

In this morning’s Herald we are told by Brendan Manning and Patrice Dougan
that “NZ ranks 23rd equal with Israel when it comes to healthy eating.” They provide a link to a report produced by Oxfam: goodenoughtoeatmediabrieffinalversionenglish.pdf

I don’t know where to start….

In spite of the report stating “[the report] is the first of its kind”, the article insists on implying several times that New Zealand’s position has changed (“The cost of food and unhealthy eating habits pushed New Zealand down the list… New Zealand has fallen well behind Australia and most of Europe in a new report ranking the healthiest places to eat in the world…. New Zealand also fell behind the United Kingdom (13), Japan (21) and the United States (21).”).

The article also says of New Zealand, “Ranked on obesity, only 13 countries out of 125 scored worse” yet provides no evidence of this and the report it links to does not have the full (or indeed, any) rankings.

It also says, “Food in Guinea, Gambia, Chad and Iran costs people 2 times more than other consumer goods, making those the most expensive countries for citizens to buy food.” What food? What consumer goods? Yesterday I bought a pie ($4.50) and a battery ($1.50). Therefore, in New Zealand, food costs 3 times more than other consumer goods. The only reference to this in the report is the statement, “the only countries where food is more expensive are Guinea (100 points) and The Gambia (97 points)” and Iran doesn’t get a mention at all.

To be fair to the journalists (although, why should we?) they are simply repeating mistakes from the Oxfam website (http://www.oxfam.org.nz/news/new-zealand-beaten-australia-oxfam-s-new-global-food-table) where it states, “Food in Guinea, The Gambia, Chad and Iran costs people two-and-a-half times more than other consumer goods, making those the most expensive countries for citizens to buy food.”

The only data provided by Oxfam is the report linked to by the Herald, which contains no rankings. The Oxfam statement does claim that “New Zealand also fell behind the United Kingdom (13), Japan (21) and the United States (21)”, and it is perhaps here where the Herald got its information. A pity it repeated it unquestioningly…

Thank you for your nominations in last week’s Stat of the Week competition.

We’ve chosen Michael MacAskill’s nomination of the Christchurch Press article: “Luck of the Irish has sex-disease downside”.

“Irish migrant rebuild workers in Christchurch might or might not have higher rates of sexually transmitted diseases than they did last year.

This story claims that there has been an increase in Irish workers in ChCh with sexually transmitted infections. It doesn’t adjust for the large increase in the total number of Irish workers in the city over the period. No figures are available for other nationalities, so we have no context to judge whether Irish are either over or even under-represented. An absolutely unqualified and uninformed (but sadly, recently re-elected) lay Health Board member is oddly enough asked to contribute his opinion. He prefixes them with the word “Statistically…” to give them more weight. He assumes that all Irish workers in ChCh are heterosexual males, and makes several causal leaps to blame local women for passing on infections.

And why exactly are we just talking about the Irish in the first place?”

There’s also a strong reaction in the comments on that article on Stuff, including someone threatening to complain to the Press Council.

Thanks for alerting us to this article Michael, and congratulations for being our Stat of the Week winner!

While Ruatara Paapu’s entry was the only nomination last week in our Stat of the Week competition, it is still a worthy winner.

Auckland Councillor Cameron Brown put out a press release entitled: “68% percent [sic] of Aucklanders wanted berm mowing continued”.

However, this statistic is rather misleading – it’s 68% of those who made a submission on berm mowing, not 68% of Aucklanders.

Congratulations Rutara and keep those nominations coming in!

Thank you for your nominations in this week’s Stat of the Week Competition.

Two of the nominations were about arithmetic – percentage increase and closing speed calculations – and two were more interesting examples about coffee and beer drinking. Thomas had posted earlier about the coffee drinking example (although Dave Tattersfield added some more useful information to his nomination).

So, this week we’ve chosen Nick Iversen’s curious sample-size-of-one beer-drinking nomination to be our Stat of the Week:

Under limit after 13 beers in 2 hours

This statistic doesn’t ring true and defies common sense.

The article says that a police officer who drank 13 beers in two hours remained under the legal drink-driving limit of 80. That’s incredible and I don’t believe it.

If we consult the tables at http://www.moderation.org/bac/bac-men.shtml we see that if a heavy 109kg man drinks 12 beers then after 2 hours his BAC would be 148 or roughly twice the limit.

The story can only be true if the police officer is much heavier than 109kg (say twice that) or if the beer is low alcohol and in either case the story is dishonestly misleading.

There appears to be a photograph of the policer office in question back in 2010 here (second from the left).

Congratulations Nick and thanks for all the nominations!

Thank you for your nominations in this week’s Stat of the Week Competition.

We have chosen Andrew Robertson’s nomination of Campbell Live’s GCSB Bill “poll” as the winner:

89% oppose the GCSB bill.

Self-selecting poll made out to be accurate by virtual of the number of people responding. They should have called it a petition, not a poll. A random Research NZ poll, asking a different question, put opposition at 52%.

Comments on this nomination from those members of the Statistics Department included:

“Self-selecting polls are an old favourite but this was a particularly egregious example, if only because of the way various politicians treated the result as being real data.”

And:

“Good use of counter evidence with a properly conducted sample survey.”

And Thomas blogged about this further.

Congratulations Andrew!

This week there were 5 nominations.

We’re awarding Nathaniel Wilson’s nomination of the NZ Herald‘s “complete ignorance of how averages work”:

Can I please nominate the New Zealand Herald, for displaying a complete ignorance of how averages work?

“Aucklanders’ rates bills have arrived in letterboxes and the figures
have come as a shock to some homeowers who have seen rises of 10 per
cent – despite the council promising an average increase of 2.9 per
cent.”

Because averages and maximums are not the same thing.

Thomas posted more about that story:

Obviously there’s nothing inconsistent about the average being 2.9% and the maximum being 10%. NZ’s average income is about $48000, but I take home somewhat more than that, and the CEO of Fonterra makes a whole lot more, and he may well not be the maximum. The average and the maximum are different. That’s not a shock.

The other point, that our nominator doesn’t make, is that rate increases are capped at 10%, and that all the people who hit the cap last year already knew that they would be seeing an increase this year, and roughly how much it would be. I know this because I live in Onehunga, where property values have gone up quite a lot, and I’m one of the people with a large rate increase. Since I read the rates notice I received last year I’m not at all shocked. I don’t have to say whether I’m happy or not, but it certainly wasn’t a surprise.

Congratulations Nathaniel, and thank you for the other nominations. Please keep them coming in!