May 7, 2012

Stat of the Week Competition: May 5-11 2012

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 May 11 2012.
  • Statistics can be bad, exemplary or fascinating.
  • The statistic must be in the NZ media during the period of May 5-11 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.


The fine print:

  • Judging will be conducted by the blog moderator in liaison with staff at the Department of Statistics, The University of Auckland.
  • The judges’ decision will be final.
  • The judges can decide not to award a prize if they do not believe a suitable statistic has been posted in the preceeding week.
  • Only the first nomination of any individual example of a statistic used in the NZ media will qualify for the competition.
  • Employees (other than student employees) of the Statistics department at the University of Auckland are not eligible to win.
  • The person posting the winning entry will receive a $20 iTunes voucher.
  • The blog moderator will contact the winner via their notified email address and advise the details of the $20 iTunes voucher to that same email address.
  • The competition will commence Monday 8 August 2011 and continue until cancellation is notified on the blog.


  • avatar
    Ben Brooks

    Statistic: It’s [Avengers movie opening] by far the biggest opening ever, shooting past the previous record of US $169.2 million for the debut of last year’s Harry Potter finale.
    Source: NZ Herald
    Date: 7 May 2012

    This is a bit iffy, because it ignores inflation, and uses a new(ish) measure. Adjusting for inflation the film would still be number one, but by a smaller margin. But because the figures aren’t available it excludes a bunch of films. According to this – and this – out of the top 20 highest selling films of, all time (total take inflation adjusted) this excludes the 1st, 3rd, 6th, 8th, 9th, 10th, 11th, 12th, 13th, and 17th biggest selling movies of all time. So not really as impressive as it initially seems.

    Also a good general example that ‘most $ ever’ headlines should be treated with a measure of caution regarding inflation.

    5 years ago

  • avatar
    Mark Bellhouse

    Statistic: A 2007 study of 9-year-olds in 35 countries found that 75 per cent of New Zealand students had suffered at least one of five forms of bullying in the previous month, higher than all other countries except Tunisia.
    Source: NZ Herald
    Date: Monday May 7, 2012

    I think the statistic is interesting and something more people should be aware of, but the main reason I think this story should be Stat of the Week is because the graphic gets the point across in a way that is easily understood and is not flashy just for the sake of it – this kind of journalism needs to be encouraged in NZ.

    5 years ago

  • avatar
    Daniel Fawcett

    Statistic: Nearly one in five Kiwis is now too poor to die.

    The most recent Statistics New Zealand death data shows 30,080 people died here in 2011, compared to 29,110 in the year to the end of March 2010.

    Those figures show 18 in every 100 people die unable to pay to bury or cremate themselves

    That data is backed up by a Sunday Star-Times reader poll that showed 20 per cent of respondents believed they’d need government assistance to be buried. Only nine per cent had funeral insurance.
    Source: Stuff
    Date: 06/05/2012

    I reckon this is pretty fascinating statistics It covers a topic most likely never considered by many, but now, because of statistics, New Zealanders have a great understanding of the number of New Zealanders who cant fund their own funeral. It’s an odd, but, very important topic expressed largely through statistics.

    5 years ago

  • avatar

    Statistic: The shortage of Mr Rights in Australia is so bad that women are being urged by a Catholic Church leader to grab and keep hold of any they can find. In Australia, there are just 86,000 single Mr Rights from the country’s 1.3 million 25- to 34-year-old men.

    In New Zealand, there are almost 49,000 more women than men aged 25-49, with the greatest imbalance in the prime relationship-forming and child-rearing age group of 30-44, according to Statistics New Zealand estimates from December last year.
    Source: NZ Herald
    Date: May 8, 2012

    This should be the Stat of the Week as not only is this very relevant news to tertiary students who fall under (or very soon will) this age group, but it is also very much against the widely held belief that there is a shortage of women in the world, not men – i.e. its a huge wake-up call for women, and a beacon of hope for single men who fall under this age bracket.

    The line “women needed to be less fussy and would “miss out” on eligible husbands if they tried to “have it all” tops it off.

    5 years ago

  • avatar
    Elizabeth Bickerton

    Statistic: Only five years ago the Youth 2007 survey of 9100 secondary school students found that only 2.9 per cent of girls, compared with 6.8 per cent of boys, admitted to bullying others at least once a week.

    Last year, 11,000 females of all ages, compared with 38,000 males, were caught by police for violent offences.
    Source: New Zealand Herald
    Date: 5:30 AM Tuesday May 8, 2012

    Stat of the week for its tedious links to the subject of the newspaper article it was found in. These stats are slightly misleading because they first refer to the youth 2007 survey when trying to support its argument in the ‘schoolgirls more violent than boys say teachers’ Herald Article, and then the seond stat goes on to say that 11,000 females of ALL AGES (so not necessarily school aged girls…) compared with 38,000 males (of all ages also?) were caught by police for violent offences. It’s understandable what the article is getting at but there could be more recent and relevant statistics to back up the teacher’s claims that schoolgirls are more violent than boys.

    5 years ago

  • avatar
    Louise Davidson

    Statistic: The road toll of 281 deaths last year was New Zealand’s lowest since 1952, and the rate of 6.4 people killed per 100,000 population has almost caught up with Australia’s 5.7.

    However Britain’s rate is almost half of New Zealand’s at 3.1 deaths and Sweden’s is just 2.8.
    Source: New Zealand Herald
    Date: Monday 7th May

    I think this should be the statistic of the week as many of the students in University are in the age group most likely to have a a fatal crash. (another statistic from the Ministry of Youth development). 15-24 year old’s (in 2007) had a rate of 21.2 road deaths per 100,000, higher than any other age group.

    The fact that New Zealand is working so hard to decrease the road deaths makes these statistics very relevant to many of us.

    5 years ago

  • avatar
    Vincent Tai

    Statistic: A claim made by researcher that jogging can increase your lifespan by as much as six years. Jogging for as little as an hour a week at a “slow or average” pace could be enough to extend a man’s life expectancy by 6.2 years and a woman’s by 5.6 years. The research is part of the ongoing Copenhagen City Heart Study, which has been monitoring 20,000 Danish men and women since 1976. Analysis of mortality rates over a period of up to 35 years showed that jogging reduced the risk of dying by 44 per cent for both men and women and increased lifespan by around six years.
    Source: NZ Herald
    Date: 9:32 AM Sunday May 6, 2012

    I think this article should be the stats of the week as the researcher claims that anyone who jogs as little as an hour a week can increase a person’s lifespan by an hour a week. This claim affects everyone, as adding 6 years to a person’s lifespan is a huge increase. However, the researcher only research people who lived in Denmark , there can be many different factors that produce this statistics, like genetics, standard of living, lifestyle. Lifespan varies from different country, this research only focuses in a small country in Europe, which is a non-sampling error, they are transferring their findings.

    5 years ago

  • avatar

    Statistic: New research has found eating berries can delay mental decline by up to two-and-a-half years.
    The study, published in the medical journal, Annals of Neurology, found women who ate at least half a cup of blueberries, or two-and-a-half cups of strawberries per week benefited most.
    Brain ageing in participants was found to be delayed by about one-and-a-half to two-and-a-half years, compared to those who ate few or no berries.
    Source: NZ Herald
    Date: 8 May 2012

    This is quite an interesting statistic because it is fascinating to see how something as simple as eating berries can be so beneficial for the brain and have positive health effects. It is also such an easy dietary modification with an amazing benefit.
    Though in saying this there may be a possible grey area in the article. The participants in this study were elder women, so could it possibly just be focusing on this specific segment of the population? Shouldn’t the benefits apply to everyone? Especially for foods such as berries as they have certain antioxidant properties which prevent the process of brain cell death. I believe it should concern people of all ages and demographics.

    5 years ago

  • avatar
    Michael Edkins

    Statistic: Nearly 15 per cent of people worldwide believe the world will end during their lifetime.
    Date: 2/5/12

    This statistic gives a valuable insight into the psyche of the human mind. It shows that most people are pessimistic.

    5 years ago

  • avatar

    Statistic: People with dogs are more lucky in love than those with cats
    Source: Stuff, Dom Post
    Date: 8 May 2012 (on line)

    Confounds correlation with causality.
    ‘If you’re having no luck walking up the aisle, then maybe you should try a stroll through the dog park instead.’
    The research found that dog owners were more likely to be in relationships than cat owners. So, we have two sets of people, dog people and cat people. They apparently have another characteristic in common — propensity to be in a relationship. It is highly likely that dog-liking and people-liking are both indications of personal preferences.
    Taking a stroll through a dog park won’t change your personal preferences or make you happier, but is more likely to leave you with smelly shoes.

    5 years ago

  • avatar
    Michael Edkins

    Statistic: 20 percent of females said they had lost their virginity at 15-years-old or younger compared to 13 percent of the males.
    Date: 22/5/07

    It appeals to almost everyone and it raises a big issue. If more parents knew this statistic, they may be more careful with what hey let their children do.

    5 years ago

  • avatar
    Savannah Post

    Statistic: Conservative Party leader Colin Craig used statistics generated by the Durex Sexual Wellbeing survey to justify his political position on providing subsidised or free contraception to New Zealand women. This statistic was then subsequently picked up and reported by other media outlets, including TV3 News on 09-05.
    Source: NZ Herald
    Date: 09-05-12

    Aside from the fact that the statistic was obviously out of date, this is a classic example of quoting a statistic without giving any other information, potentially misleading readers and/or viewers. Quoting the number of men the average New Zealand woman has supposedly slept with in isolation gives no concept of how this statistic compares to similar countries, how the results were collected, which countries were included etc.
    A disappointing misuse of statistics to promote the somewhat outdated concept that any woman who uses contraception is automatically promiscuous.

    5 years ago

  • avatar
    Patricia de Guzman

    Statistic: “Conservative Party leader Colin Craig’s comment that New Zealand women are the most promiscuous in the world”

    “A spokesperson said Mr Craig was using data from surveys by condom manufacturer Durex and Marie Claire magazine, where New Zealand women reported having an average of 20.4 sexual partners – nearly triple the global average of 7.3.”
    Source: MSN news (NZ)
    Date: 09.05.12

    Mr Craig has made this wild claim that young NZ women are the most promiscuous in the world when all he’s citing his information from are surveys conducted by a condom manufacturer (obviously people buying condoms will be having more sex; why buy them if you’re not planning on using them?) and Marie Claire (known to have sex info thus women reading this magazine are likely to be having more sex anyway).

    Long story short, the sample from those surveys are not a representative of the NZ population of women. We don’t want the world thinking NZ women are promiscuous when there’s no proper evidence!

    5 years ago

  • avatar

    Statistic: The study, commissioned by the Treasury after a request from Mr English, shows only a quarter of those in the bottom 10 per cent of incomes in 2002 were still there in 2009.
    Source: Dominion Post
    Date: 10 May 2012

    I think the article misrepresents the study findings. It confuses ‘low income’ (a dollar measure) with decile (a rank measure), and also seems to confuse decile and quintile.

    From the report:

    – Income mobility similar at top and bottom:
    ‘From wave 1]7, overall mobility in income was higher, with around 50% of those who
    started out in the lowest or highest quintile ending the study period in the same quintile.’

    – Persistence of low incomes:
    ‘Of those who were in low
    income at wave 1; 65% remained in low income at wave 2; 50% were in low income in wave
    7; a quarter were in low income for all seven waves.’
    Note that one-quarter were low-income for a full 7 waves, but half of 2002 low-income households were again low-income in 2009. The article doesn’t make the distinction.

    5 years ago

  • avatar
    Toby Manhire

    Statistic: Paula Bennett citing in parliament online/text polls as evidence of support for her contraception-for-beneficiaries policy
    Source: Hansard
    Date: Tuesday

    5 years ago

  • avatar
    Nick Iversen

    Statistic: Poll of 1004 people has a margin of error of 3.9%.
    Source: New Zealand Herald
    Date: 10 May 2012

    I thought that the margin of error reported for this poll was interesting. It differs from that usually reported for NZ polls.

    If you take 1.96*sqrt(p*(1-p)/n) and use pp=0.5 and n=1004 you get a margin or error of 3.1% which is what is usually reported for NZ polls (see e.g. That assumes that the sample is representative of the population.

    It seldom is though which introduces a source of error that the 3.1% doesn’t account for.

    The US poll uses 3.9%. I wonder if they are accounting for sampling bias as well as sampling error. Sounds to me like the US pollsters are doing a more sophisticated measure of error than NZ ones.

    Check out their methodology at

    5 years ago