April 27, 2017

On debates about data

On Wednesday, the NZ Herald website featured a story and graphics by Harkanwal Singh and Lincoln Tan on immigration. This story was based on permanent and long-term migration data from Statistics New Zealand. The graphics allowed readers to explore the data for themselves. The data source was accurately described and was well targeted to the current political discussion about changing immigration policies.

The specific data set and visualisation used are not the only possible ones, and reasoned criticism of the data and analyses is entirely legitimate. StatsChat encourages that sort of thing. We have done it ourselves, and we have published links when other people do it.

Winston Peters, however, claimed that the Herald story was “fake news” and attributed the conclusions to the reporters being Asian immigrants themselves. The first claim is factually incorrect; the second (in the absence of convincing evidence) is outrageous.

James Curran (Professor of Statistics)
Thomas Lumley (Professor of Statistics)
Chris Triggs (Professor of Statistics)

avatar

Thomas Lumley (@tslumley) is Professor of Biostatistics at the University of Auckland. His research interests include semiparametric models, survey sampling, statistical computing, foundations of statistics, and whatever methodological problems his medical collaborators come up with. He also blogs at Biased and Inefficient See all posts by Thomas Lumley »

Comments

  • avatar
    steve curtis

    How come the Herald story lists Australia as among the ‘top 5’ place of origin for work visas, when Australians dont require a visa to work here ( nor the other way round)

    8 years ago

    • avatar
      Thomas Lumley

      Because it’s by country of previous residence, not by citizenship.

      Also because some Australians get visas. I have a residence visa because if I didn’t have one I’d only be an NZ resident while I was in the country, not while I was travelling.

      8 years ago

      • avatar
        steve curtis

        The story was about ‘work visas’. There is whole raft of other types, education residency, family reunion etc and of course some types can be changed without leaving the country.

        Looking at the arrival card details it asks 3 separate questions about ‘origin’
        1) nationality on passport
        2) last country lived in for 12 months or more
        3)Overseas port where you boarded this aircraft

        Its not clear what of these answers was ‘counted’, no doubt the politicians will use the ones best suited to their purpose

        8 years ago

        • avatar
          Thomas Lumley

          It was country of previous residence. I know because I checked with the journalists.

          8 years ago

  • avatar
    John Egan

    Peters is a piece of garbage. And makes stuff up all the time.

    8 years ago

  • avatar
    Megan Pledger

    I don’t think Winston Peters should have made it personal i.e. names, let alone ethnicities, but he was probably look for a distraction after the 12 year old’s rant didn’t go down that well on ANZAC day.

    However, all I could see (from the link you provided) about where the data came from was that it came from StatsNZ – nothing about it being based on arrival card information. StatsNZ collect a lot of data so there does need to be more clarity about what the original data source was.

    And, secondly, the heading is “Explore which countries are most likely to be affected by proposed changes in immigration rules.”

    That does sound more like it’s based on origin (i.e. nationality) of the person involved rather than the rather obscure “last country lived in for 12 months or more”. Who is going to guess that is what they were anlaysing (unless it was a someone’s specialised area). It’s not like Australia is going to give two hoots about a South African migrant who has been living there for 12 months who then moves to NZ.

    Altogether, I think the whole thing just needed some more thinking through before publication but that’s not always an option when the authors work for a newspaper.

    8 years ago

  • avatar
    steve curtis

    Isnt it the usual story about any data driven story given prominence in the media- what are they really counting.
    In this era surely the Immigration service computers can easily give up
    for the last 12 months,the number of work visas issued ( and re-issued) by country of nationality, age, occupation etc.
    I have worked with many migrants over the years, and on the whole for technical jobs they were ‘over qualified’

    8 years ago

    • avatar
      Megan Pledger

      I think the problem with immigration services data is that they just issue visas and they don’t know when or if the people come. That’s why people have to look at the “arrival card” information if they want to know about who is actually here.

      Which makes me wonder, what happened to people who changed status while here e.g. from tourist to a work visa.

      8 years ago