English subtitles

← Why statistics are fascinating: the numbers are us | Alan Smith | TEDxExeter

Get Embed Code
16 Languages

Showing Revision 4 created 01/31/2017 by Krystian Aparta.

  1. Back in 2003,
  2. the UK government carried out a survey.
  3. And it was a survey that measured
    levels of numeracy
  4. in the population.
  5. And they were shocked to find out
  6. that for every 100 working age
    adults in the country,
  7. 47 of them lacked Level 1 numeracy skills.
  8. Now, Level 1 numeracy skills --
    that's low-end GCSE score.
  9. It's the ability to deal with fractions,
    percentages and decimals.
  10. So this figure prompted
    a lot of hand-wringing in Whitehall.
  11. Policies were changed,
  12. investments were made,
  13. and then they ran
    the survey again in 2011.
  14. So can you guess
    what happened to this number?
  15. It went up to 49.
  16. (Laughter)

  17. And in fact, when I reported
    this figure in the FT,

  18. one of our readers joked and said,
  19. "This figure is only shocking
    to 51 percent of the population."
  20. (Laughter)

  21. But I preferred, actually,
    the reaction of a schoolchild

  22. when I presented
    at a school this information,
  23. who raised their hand and said,
  24. "How do we know that the person
    who made that number
  25. isn't one of the 49 percent either?"
  26. (Laughter)

  27. So clearly, there's a numeracy issue,

  28. because these are
    important skills for life,
  29. and a lot of the changes
    that we want to introduce in this century
  30. involve us becoming
    more comfortable with numbers.
  31. Now, it's not just an English problem.
  32. OECD this year released some figures
    looking at numeracy in young people,
  33. and leading the way, the USA --
  34. nearly 40 percent of young people
    in the US have low numeracy.
  35. Now, England is there too,
  36. but there are seven OECD countries
    with figures above 20 percent.
  37. That is a problem,
    because it doesn't have to be that way.
  38. If you look at the far end of this graph,
  39. you can see the Netherlands and Korea
    are in single figures.
  40. So there's definitely a numeracy
    problem that we want to address.
  41. Now, as useful as studies like these are,

  42. I think we risk herding people
    inadvertently into one of two categories;
  43. that there are two kinds of people:
  44. those people that are comfortable
    with numbers, that can do numbers,
  45. and the people who can't.
  46. And what I'm trying
    to talk about here today
  47. is to say that I believe
    that is a false dichotomy.
  48. It's not an immutable pairing.
  49. I think you don't have to have
    tremendously high levels of numeracy
  50. to be inspired by numbers,
  51. and that should be the starting point
    to the journey ahead.
  52. And one of the ways in which
    we can begin that journey, for me,

  53. is looking at statistics.
  54. Now, I am the first to acknowledge
    that statistics has got somewhat
  55. of an image problem.
  56. (Laughter)

  57. It's the part of mathematics

  58. that even mathematicians
    don't particularly like,
  59. because whereas the rest of maths
    is all about precision and certainty,
  60. statistics is almost the reverse of that.
  61. But actually, I was a late convert
    to the world of statistics myself.
  62. If you'd asked my undergraduate professors
  63. what two subjects would I be least likely
    to excel in after university,
  64. they'd have told you statistics
    and computer programming,
  65. and yet here I am, about to show you
    some statistical graphics
  66. that I programmed.
  67. So what inspired that change in me?

  68. What made me think that statistics
    was actually an interesting thing?
  69. It's really because
    statistics are about us.
  70. If you look at the etymology
    of the word statistics,
  71. it's the science of dealing with data
  72. about the state or the community
    that we live in.
  73. So statistics are about us as a group,
  74. not us as individuals.
  75. And I think as social animals,
  76. we share this fascination about how
    we as individuals relate to our groups,
  77. to our peers.
  78. And statistics in this way
    are at their most powerful
  79. when they surprise us.
  80. And there's been some really wonderful
    surveys carried out recently

  81. by Ipsos MORI in the last few years.
  82. They did some really interesting stuff.
  83. They did a survey
    of over 1,000 adults in the UK,
  84. and said, for every 100 people
    in England and Wales,
  85. how many of them are Muslim?
  86. Now the average answer from this survey,
  87. which was supposed to be representative
    of the total population ...
  88. was 24.
  89. That's what people thought.
  90. British people think 24 out of every 100
    people in the country are Muslim.
  91. Now, official figures reveal
    that figure to be about five.
  92. So there's this big variation
    between what we think, our perception,
  93. and the reality as given by statistics.
  94. And I think that's interesting.
  95. What could possibly be causing
    that misperception?
  96. And I was so thrilled with this study,

  97. I started to take questions out
    in presentations. I was referring to it.
  98. Now, I did a presentation
  99. at St. Paul's School for Girls
    in Hammersmith,
  100. and I had an audience rather like this,
  101. except it was comprised entirely
    of sixth-form girls.
  102. And I said, "Girls,
  103. how many teenage girls do you think
    the British public think
  104. get pregnant every year?"
  105. And the girls were apoplectic when I said
  106. the British public think that 15
    out of every 100 teenage girls
  107. get pregnant in the year.
  108. And they had every right to be angry,
  109. because in fact, I'd have to have
    closer to 200 dots
  110. before I could color one in,
  111. in terms of what
    the official figures tell us.
  112. And rather like numeracy,
    this is not just an English problem.

  113. Ipsos MORI expanded the survey
    in recent years to go across the world.
  114. And so, they asked Saudi Arabians,
  115. for every 100 adults in your country,
  116. how many of them are overweight or obese?
  117. And the average answer from the Saudis
    was just over a quarter.
  118. That's what they thought.
  119. Just over a quarter of adults
    are overweight or obese.
  120. The official figures show, actually,
    it's nearer to three-quarters.
  121. (Laughter)

  122. So again, a big variation.

  123. And I love this one: they asked in Japan,
    they asked the Japanese,

  124. for every 100 Japanese people,
  125. how many of them live in rural areas?
  126. The average was about a 50-50 split,
    just over halfway.
  127. They thought 56 out of every 100
    Japanese people lived in rural areas.
  128. The official figure is seven.
  129. So extraordinary variations,
    and surprising to some,

  130. but not surprising to people
    who have read the work
  131. of Daniel Kahneman, for example,
    the Nobel-winning economist.
  132. He and his colleague, Amos Tversky,
    spent years researching this disjoint
  133. between what people perceive
    and the reality,
  134. the fact that people are actually
    pretty poor intuitive statisticians.
  135. And there are many reasons for this.
  136. Individual experiences, certainly,
    can influence our perceptions,
  137. but so, too, can things like the media
    reporting things by exception,
  138. rather than what's normal.
  139. Kahneman had a nice way
    of referring to that.
  140. He said, "We can be blind
    to the obvious" --
  141. so we've got the numbers wrong --
  142. "but we can be blind
    to our blindness about it."
  143. And that has enormous
    repercussions for decision making.
  144. So at the statistics office
    while this was all going on,

  145. I thought this was really interesting.
  146. I said, this is clearly a global problem,
  147. but maybe geography is the issue here.
  148. These were questions that were all about,
    how well do you know your country?
  149. So in this case, it's how well
    do you know 64 million people?
  150. Not very well, it turns out.
    I can't do that.
  151. So I had an idea,
  152. which was to think about
    this same sort of approach
  153. but to think about it
    in a very local sense.
  154. Is this a local?
  155. If we reframe the questions and say,
  156. how well do you know your local area,
  157. would your answers be any more accurate?
  158. So I devised a quiz:

  159. How well do you know your area?
  160. It's a simple Web app.
  161. You put in a post code
  162. and then it will ask you questions
    based on census data
  163. for your local area.
  164. And I was very conscious
    in designing this.
  165. I wanted to make it open
    to the widest possible range of people,
  166. not just the 49 percent
    who can get the numbers.
  167. I wanted everyone to engage with it.
  168. So for the design of the quiz,
  169. I was inspired by the isotypes
  170. of Otto Neurath from the 1920s and '30s.
  171. Now, these are methods
    for representing numbers
  172. using repeating icons.
  173. And the numbers are there,
    but they sit in the background.
  174. So it's a great way
    of representing quantity
  175. without resorting to using terms
    like "percentage,"
  176. "fractions" and "ratios."
  177. So here's the quiz.

  178. The layout of the quiz is,
  179. you have your repeating icons
    on the left-hand side there,
  180. and a map showing you the area
    we're asking you questions about
  181. on the right-hand side.
  182. There are seven questions.
  183. Each question, there's a possible answer
    between zero and a hundred,
  184. and at the end of the quiz,
  185. you get an overall score
    between zero and a hundred.
  186. And so because this is TEDxExeter,
  187. I thought we would have
    a quick look at the quiz
  188. for the first few questions of Exeter.
  189. And so the first question is:
  190. For every 100 people,
    how many are aged under 16?
  191. Now, I don't know Exeter very well
    at all, so I had a guess at this,
  192. but it gives you an idea
    of how this quiz works.
  193. You drag the slider
    to highlight your icons,
  194. and then just click "Submit" to answer,
  195. and we animate away the difference
    between your answer and reality.
  196. And it turns out, I was a pretty
    terrible guess: five.
  197. How about the next question?

  198. This is asking about
    what the average age is,
  199. so the age at which half
    the population are younger
  200. and half the population are older.
  201. And I thought 35 -- that sounds
    middle-aged to me.
  202. (Laughter)

  203. Actually, in Exeter,
    it's incredibly young,

  204. and I had underestimated the impact
    of the university in this area.
  205. The questions get harder
    as you go through.
  206. So this one's now asking
    about homeownership:
  207. For every 100 households, how many
    are owned with a mortgage or loan?
  208. And I hedged my bets here,
  209. because I didn't want to be
    more than 50 out on the answer.
  210. (Laughter)

  211. And actually, these get harder,
    these questions,

  212. because when you're in an area,
    when you're in a community,
  213. things like age -- there are clues
    to whether a population is old or young.
  214. Just by looking around
    the area, you can see it.
  215. Something like homeownership
    is much more difficult to see,
  216. so we revert to our own heuristics,
  217. our own biases about how many people
    we think own their own homes.
  218. Now the truth is,
    when we published this quiz,

  219. the census data that it's based on
    was already a few years old.
  220. We've had online applications
    that allow you to put in a post code
  221. and get statistics back for years.
  222. So in some senses,
  223. this was all a little bit old
    and not necessarily new.
  224. But I was interested to see
    what reaction we might get
  225. by gamifying the data
    in the way that we have,
  226. by using animation
  227. and playing on the fact
    that people have their own preconceptions.
  228. It turns out, the reaction was, um ...

  229. was more than I could have hoped for.
  230. It was a long-held ambition of mine
    to bring down a statistics website
  231. due to public demand.
  232. (Laughter)

  233. This URL contains the words
    "statistics," "gov" and "UK,"

  234. which are three of people's least
    favorite words in a URL.
  235. And the amazing thing about this
    was that the website came down
  236. at quarter to 10 at night,
  237. because people were actually
    engaging with this data
  238. of their own free will,
  239. using their own personal time.
  240. I was very interested to see
  241. that we got something like
    a quarter of a million people
  242. playing the quiz within the space
    of 48 hours of launching it.
  243. And it sparked an enormous discussion
    online, on social media,
  244. which was largely dominated
  245. by people having fun
    with their misconceptions,
  246. which is something that
    I couldn't have hoped for any better,
  247. in some respects.
  248. I also liked the fact that people started
    sending it to politicians.
  249. How well do you know the area
    you claim to represent?
  250. (Laughter)

  251. And then just to finish,

  252. going back to the two kinds of people,
  253. I thought it would be
    really interesting to see
  254. how people who are good with numbers
    would do on this quiz.
  255. The national statistician
    of England and Wales, John Pullinger,
  256. you would expect he would be pretty good.
  257. He got 44 for his own area.
  258. (Laughter)

  259. Jeremy Paxman -- admittedly,
    after a glass of wine ...

  260. 36.
  261. Even worse.
  262. It just shows you that the numbers
    can inspire us all.
  263. They can surprise us all.
  264. So very often, we talk about statistics

  265. as being the science of uncertainty.
  266. My parting thought for today is:
  267. actually, statistics is the science of us.
  268. And that's why we should
    be fascinated by numbers.
  269. Thank you very much.

  270. (Applause)