September 10, 2012

Stat of the Week Competition: September 8 – 14 2012

By

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 September 14 2012.
  • Statistics can be bad, exemplary or fascinating.
  • The statistic must be in the NZ media during the period of September 8 – 14 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.
  • Individual posts on Stats Chat are just the opinions of their authors, who can criticise anyone who they feel deserves it, but the Stat of the Week award involves the Department of Statistics more officially. For that reason, we will not award Stat of the Week for a statistic coming from anyone at the University of Auckland outside the Statistics department. You can still nominate and discuss them, but the nomination won’t be eligible for the prize.
  • 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

Rachel Cunliffe is the co-director of CensusAtSchool and currently consults for the Department of Statistics. Her interests include statistical literacy, social media and blogging. See all posts by Rachel Cunliffe »

Nominations

  • avatar
    Mike Dickison

    Statistic: The NZ Herald’s first interactive map, of NZ crime hotspots, is a disappointment. First, as Keith Ng has pointed out, it shows only that Auckland has more people than Pukekohe. Second, the circles aren’t in proportion: the larger one in this screenshot (mlkshk.com/r/J8X1.jpeg) is three times the area it should be.
    Source: New Zealand Herald
    Date: Sept 10 2012

    The NZ Herald has been touting its infographics as a new feature of the remodelled paper, launched only yesterday, and the editor boasted they’ve been getting help from the Stats Department to improve its reporters’ numeracy. So we wouldn’t have been expecting simple errors like this.

    12 years ago

  • avatar
    Nick Iversen

    Statistic: Small trends cannot be measured if there is error in the data.
    Source: New Zealand Herald
    Date: 11 Sep 2012

    Chris de Freitas says “Temperature trends detected are small, usually just a few tenths of one degree Celsius over 100 years, a rate that is exceeded by the data’s standard error. Statistically this means the trend is indistinguishable from zero.”

    This is not true. Trends CAN be measured more accurately than the data themselves.

    Technically, no matter how much uncertainty there is in the data, if you have either (1) enough data or (2) a long enough time series you can measure a trend as accurately as you want even if the trend is tiny compared to the variation in the data.

    For the geeks:

    As an example, I refer you to http://en.wikipedia.org/wiki/Student%27s_t-test#Slope_of_a_regression_line – look at the formula under “standard error of the slope coefficient.”

    As n increases (i.e. as more data is collected) the error gets smaller. As the time series gets longer the x values get more dispersed and the denominator denominator gets larger. So the error gets smaller again.

    12 years ago