9:59:59.000,9:59:59.000 The world we live in is awashed with data 9:59:59.000,9:59:59.000 that comes pouring in from everywhere around us. 9:59:59.000,9:59:59.000 On it own, this data is just noise and confusion. 9:59:59.000,9:59:59.000 To make sense of data, to find the meaning in it, 9:59:59.000,9:59:59.000 we need a powerful branch of science: statistics. 9:59:59.000,9:59:59.000 Believe me, there's nothing boring about statistics 9:59:59.000,9:59:59.000 especially not today, when we can make the data sing. 9:59:59.000,9:59:59.000 With statistics we can really make sense of the world. 9:59:59.000,9:59:59.000 Are statistics, the data diluge as it's been called, 9:59:59.000,9:59:59.000 leading us to a greater understanding 9:59:59.000,9:59:59.000 of the life on Earth and the world beyond? 9:59:59.000,9:59:59.000 Thanks to incredible power of today's computers 9:59:59.000,9:59:59.000 it may fundamentally transform the process of scientific discovery. 9:59:59.000,9:59:59.000 I kid you not, statistics is now the sexiest subject around. 9:59:59.000,9:59:59.000 Did you know that there's is one million boats in Sweden? 9:59:59.000,9:59:59.000 That's one boat per nine people. 9:59:59.000,9:59:59.000 It's the highest number of boats per person in Europe. 9:59:59.000,9:59:59.000 Being statistician, you don't like telling your profession at dinner parties, 9:59:59.000,9:59:59.000 but really, statisticians shouldn't be shy 9:59:59.000,9:59:59.000 because they always want to understand what's going on. 9:59:59.000,9:59:59.000 Stastistics gives us a persperctive of the world we live in 9:59:59.000,9:59:59.000 that we can't get in any other way. 9:59:59.000,9:59:59.000 Statistics tells us whether the things we think and believe are actually true. 9:59:59.000,9:59:59.000 Statistics are far more useful than we usually like to admit. 9:59:59.000,9:59:59.000 In the last recession, there was this famous call into Talk Radio Station. 9:59:59.000,9:59:59.000 The man complained: "in times like this, when unemployment rates are up to 13%, 9:59:59.000,9:59:59.000 and income has fallen by 5%, and suicide rates are climbing, 9:59:59.000,9:59:59.000 I get so angry that the government is wasting money on things like correctional statistics." 9:59:59.000,9:59:59.000 I'm not oficially a statistician, strictly speaking my field is global health. 9:59:59.000,9:59:59.000 But I got really obsessed with stats, when I realised how many people in Sweden 9:59:59.000,9:59:59.000 don't know anything about the rest of the world. 9:59:59.000,9:59:59.000 I started in our Medical University in Karolinksa Institute, 9:59:59.000,9:59:59.000 an ungraduate course called Global Health. 9:59:59.000,9:59:59.000 These students coming to us have actually the highest grades you can get in theSwedish college system. 9:59:59.000,9:59:59.000 So I thought maybe they know everything I'm going to teach them. 9:59:59.000,9:59:59.000 So I did a pre-test when they came. 9:59:59.000,9:59:59.000 One of the questions, from which I learnt a lot, was: 9:59:59.000,9:59:59.000 Which country has the highest child mortality of these five pairs? 9:59:59.000,9:59:59.000 I won't put you at test here, but it's Turkey which is higher there, 9:59:59.000,9:59:59.000 Poland, Russia, Pakistan and South Africa. 9:59:59.000,9:59:59.000 And these were the results of the Swedish students. 9:59:59.000,9:59:59.000 1.8 answers right out of 5 possible, 9:59:59.000,9:59:59.000 that means that there was a place for a professor in International Health 9:59:59.000,9:59:59.000 and for my course. 9:59:59.000,9:59:59.000 But one late night when I was compiling my report 9:59:59.000,9:59:59.000 I really realise my discovery. 9:59:59.000,9:59:59.000 I have shown that Swedish top students know 9:59:59.000,9:59:59.000 statistically significantly less about the world than the chimpanzees. 9:59:59.000,9:59:59.000 Beacuse the chimpanzee would score half right. 9:59:59.000,9:59:59.000 If I gave them two bananas with Sri Lanka and Turkey 9:59:59.000,9:59:59.000 they would be right half of the cases. 9:59:59.000,9:59:59.000 But the students are not there. 9:59:59.000,9:59:59.000 I did also an unethical study of the professors of the Karolinska Institute 9:59:59.000,9:59:59.000 that hands out the Nobel Prize in Medicine, and they aren't on par with the chimpanzee. 9:59:59.000,9:59:59.000 Today, there's more information accesible than ever before, 9:59:59.000,9:59:59.000 and I work with my team at the Gapminder Foundation 9:59:59.000,9:59:59.000 using new tools that help everyone make sense of the changing world. 9:59:59.000,9:59:59.000 We draw on the masses of data that are now free available 9:59:59.000,9:59:59.000 from international institutions like the UN and the World Bank. 9:59:59.000,9:59:59.000 It's become my mission to share my insights from this data 9:59:59.000,9:59:59.000 with anyone who listen, and to reveal how statistics [br]is nothing to be frightened of. 9:59:59.000,9:59:59.000 I'm going to provide you a view [br]of the global health situation across mankind, 9:59:59.000,9:59:59.000 and I'm going to do that in a hopefully enjoyable way. [br]So relax. 9:59:59.000,9:59:59.000 We did this software which displays it like this, 9:59:59.000,9:59:59.000 every bubble here is a country, this is China, this is India. 9:59:59.000,9:59:59.000 The size of the bubble is the population. 9:59:59.000,9:59:59.000 And I'm going to stage a race here 9:59:59.000,9:59:59.000 between this sort of yellow Ford here, and the red Toyota down there, 9:59:59.000,9:59:59.000 and the brownish Volvo. 9:59:59.000,9:59:59.000 The Toyota has a very bad start down here, 9:59:59.000,9:59:59.000 and United States' Ford is going off road there, 9:59:59.000,9:59:59.000 and the Volvo is doing quite fine, this is the war, 9:59:59.000,9:59:59.000 they Toyota got off crack, now Toyota is coming on the healthier side of Sweden. 9:59:59.000,9:59:59.000 That's the point when I sold the Volvo and bought the Toyota. 9:59:59.000,9:59:59.000 This is the Great Leap Forward when China fell down, 9:59:59.000,9:59:59.000 it was central planning by Mao Tse Tung, 9:59:59.000,9:59:59.000 China recovered and said "never more stupid central planning", but they went up here. 9:59:59.000,9:59:59.000 No, there was one more inequity, look there! United States! 9:59:59.000,9:59:59.000 Oh, they broke my frame! 9:59:59.000,9:59:59.000 Washington D.C. is so rich over there, but it's not as healthy as Kerala, India. 9:59:59.000,9:59:59.000 It's quite interesting, isn't it? 9:59:59.000,9:59:59.000 Welcome to the USA, world leaders in big cars 9:59:59.000,9:59:59.000 and free data. 9:59:59.000,9:59:59.000 There are many here who share my vision 9:59:59.000,9:59:59.000 of making public data accesible and useful for everyone. 9:59:59.000,9:59:59.000 The city of San Francisco is in the lead, opening up it's data on everything. 9:59:59.000,9:59:59.000 Even the Police Dept. is releasing all it's crime reports. 9:59:59.000,9:59:59.000 This official crime data has been turned into a wonderful inteactive map 9:59:59.000,9:59:59.000 by two of the cities computer whizzes. 9:59:59.000,9:59:59.000 It's community statistics in action. 9:59:59.000,9:59:59.000 Crimespotting is a map of crime reports 9:59:59.000,9:59:59.000 from the San Francisco Police Dept. 9:59:59.000,9:59:59.000 showing dots on maps for citizens to be able to see patterns of crime 9:59:59.000,9:59:59.000 in their neighbourhoods in San Francisco. 9:59:59.000,9:59:59.000 The map is not just about individual crimes 9:59:59.000,9:59:59.000 but about broader patterns that show [br]you where crime is clustered around the city, 9:59:59.000,9:59:59.000 which have high crime, [br]which areas have relatively low crime. 9:59:59.000,9:59:59.000 We're here at top of Jones Street, on uphill, [br]quite a nice neighbourhood 9:59:59.000,9:59:59.000 what the crime maps show us is the relationship between typography and crime. 9:59:59.000,9:59:59.000 The higher up the hill, the less crime there is. 9:59:59.000,9:59:59.000 We crossed over the border into the flats. 9:59:59.000,9:59:59.000 Essentially, as soon as you get into the kind of lower line areas of Jones street, 9:59:59.000,9:59:59.000 the crime just skyrockets. 9:59:59.000,9:59:59.000 So we're in the uptown Tenderloin District, 9:59:59.000,9:59:59.000 it's one of the oldest and most dangerous [br]neighbourhoods in San Francisco. 9:59:59.000,9:59:59.000 This is where you go to buy drugs, [br]right around here. 9:59:59.000,9:59:59.000 You see lots of aggreviated assault,[br]lots of thefts. 9:59:59.000,9:59:59.000 Basically, the huge part of the crime of the city [br]happens right in these four or six block areas. 9:59:59.000,9:59:59.000 If you've been hearing police sirens[br]in your neighbourhood, 9:59:59.000,9:59:59.000 you can use the map to find out why. 9:59:59.000,9:59:59.000 If you are out at night in an unfamiliar part of town 9:59:59.000,9:59:59.000 you can check the map for streets to avoid. 9:59:59.000,9:59:59.000 If a neighbour gets burglared, you can see, 9:59:59.000,9:59:59.000 is it the one off or has there been a spike in local crime? 9:59:59.000,9:59:59.000 If you commute through a neighbourhood and you're worried about its safety 9:59:59.000,9:59:59.000 the fact that we have the ability to turn off all the night time and middle-of-the-day crimes 9:59:59.000,9:59:59.000 and show you just the things that are happening during your commute, 9:59:59.000,9:59:59.000 is a statistical operation but I think to the people [br]that are interacting with the thing 9:59:59.000,9:59:59.000 it feels very much more like [br]they just are sort of browsing a website 9:59:59.000,9:59:59.000 or shopping on Amazon. [br]They're looking at data, 9:59:59.000,9:59:59.000 and they don't realise that they're doing statistics. 9:59:59.000,9:59:59.000 What's most exciting for me is that public statistics 9:59:59.000,9:59:59.000 is making citizens more powerful [br]and the authorities more accountable. 9:59:59.000,9:59:59.000 We have community meetings that the police attend 9:59:59.000,9:59:59.000 and what citizens are now doing, [br]they're bringing printouts of the maps 9:59:59.000,9:59:59.000 to show where crimes are taking place, 9:59:59.000,9:59:59.000 and they're demanding services [br]from the police department, 9:59:59.000,9:59:59.000 which is now having to change how they please, 9:59:59.000,9:59:59.000 how they provide policing services, 9:59:59.000,9:59:59.000 because the data is showing [br]what is working and what is not. 9:59:59.000,9:59:59.000 People in San Francisco are also using public data 9:59:59.000,9:59:59.000 to map social inequalities, [br]and see how to improve society 9:59:59.000,9:59:59.000 and the possibilities are endless. 9:59:59.000,9:59:59.000 Our dream would be that the government announced that 9:59:59.000,9:59:59.000 this data project would really focus on live information 9:59:59.000,9:59:59.000 on stuff that was being reported [br]and pushed out into the world as it was happening. 9:59:59.000,9:59:59.000 Trash pickup, traffic accidents, buses, 9:59:59.000,9:59:59.000 and through the kind of the stats gathering power on the internet 9:59:59.000,9:59:59.000 it's posible to really see the workings of the city 9:59:59.000,9:59:59.000 displayed as a unified interface. 9:59:59.000,9:59:59.000 That's where we are heading, 9:59:59.000,9:59:59.000 towards a world of free data [br]with all the statistical insights that come from it 9:59:59.000,9:59:59.000 accesible to everyone, empowering us as citizens 9:59:59.000,9:59:59.000 and letting hold our rulers to account. 9:59:59.000,9:59:59.000 It's a long way from where statistics began. 9:59:59.000,9:59:59.000 Statistics are essential to monitor our government in our societies. 9:59:59.000,9:59:59.000 But, it was our rulers out there who started the collection of statistics 9:59:59.000,9:59:59.000 in first place in order to monitor us. 9:59:59.000,9:59:59.000 In fact the word statistics comes from state. 9:59:59.000,9:59:59.000 Modern statistics began two centuries ago. 9:59:59.000,9:59:59.000 Once it got going it spread and never stopped. 9:59:59.000,9:59:59.000 And guess who was first. 9:59:59.000,9:59:59.000 The Chinese have Confucious, [br]the Italians have Da Vinci, 9:59:59.000,9:59:59.000 and the British have Shakespeare, and we have the Tabellverket 9:59:59.000,9:59:59.000 the first ever systematic collection of statistics. 9:59:59.000,9:59:59.000 Since the year 1749 we have collected data on every birth, marriage and death 9:59:59.000,9:59:59.000 and we are proud of it. 9:59:59.000,9:59:59.000 The Tabellverket recorded information from every parish in Sweden. 9:59:59.000,9:59:59.000 It was a huge quantity of data[br]and it was the first time any goverment 9:59:59.000,9:59:59.000 could get any accurate picture of its people. 9:59:59.000,9:59:59.000 Sweden had been the greatest military power in Northern Europe 9:59:59.000,9:59:59.000 but by 1749 our star was really fading and other countries were growing stronger. 9:59:59.000,9:59:59.000 At least though, we were a large power, thought to have 20 million people 9:59:59.000,9:59:59.000 enough to rival Britain and France. 9:59:59.000,9:59:59.000 But we were in for a nasty surprise. 9:59:59.000,9:59:59.000 The first analysis of Tabellverket revealed that Sweden only had 2 million inhabitants. 9:59:59.000,9:59:59.000 Sweden was not only a power in decline, it also had a very small popoulation. 9:59:59.000,9:59:59.000 The government was horrified by this finding. 9:59:59.000,9:59:59.000 What if the enemy found out? 9:59:59.000,9:59:59.000 But the Tabellverket also showed that many women die in childbirth. 9:59:59.000,9:59:59.000 And many children died young, and government took action to improve the health of the people. 9:59:59.000,9:59:59.000 That was the beginning of modern Sweden. 9:59:59.000,9:59:59.000 It took more than 50 years before the Austrians, Belgiums, Danes, Dutch, 9:59:59.000,9:59:59.000 Germans, Italians and finally the British caught up with Sweden 9:59:59.000,9:59:59.000 in collecting and using statistics. 9:59:59.000,9:59:59.000 It was called political arithmethic, [br]and it was a lovely phrase as use for statistics. 9:59:59.000,9:59:59.000 Governments could have much more control [br]and understanding of the society 9:59:59.000,9:59:59.000 how it's working, how it's developing, 9:59:59.000,9:59:59.000 and essentially, so they could control it better. 9:59:59.000,9:59:59.000 It wasn't just governments [br]who woke up to the power of statistics. 9:59:59.000,9:59:59.000 Right across Europe, 19th century society went mad for facts. 9:59:59.000,9:59:59.000 And despite its late start, Britain with its Royal Statistical Society in London 9:59:59.000,9:59:59.000 was soon a statisticians' nirvana. 9:59:59.000,9:59:59.000 I love looking at old copies of the Royal Statistical Society, 9:59:59.000,9:59:59.000 because is full of this stuff. 9:59:59.000,9:59:59.000 There's a wonderful paper from the 1840s 9:59:59.000,9:59:59.000 which shows a map of England [br]and the rates of bastardy of each county 9:59:59.000,9:59:59.000 9:59:59.000,9:59:59.000 so you can identify very quickly the areas [br]with high areas of bastardy. 9:59:59.000,9:59:59.000 Being in East Anglia makes me slightly laugh 9:59:59.000,9:59:59.000 that Norfolk was on top of the bastardy league in the 1840s. 9:59:59.000,9:59:59.000 One of the founders of the Royal Statistical Society 9:59:59.000,9:59:59.000 was the great victorian mathematician and inventor Charles Babbage. 9:59:59.000,9:59:59.000 In 1842 he read the latest poem [br]by a equally great victorian 9:59:59.000,9:59:59.000 Alfred Tennyson. 9:59:59.000,9:59:59.000 "Vision of Sin" contained the lines: 9:59:59.000,9:59:59.000 "Fill the cup and fill the can, [br]Have a rouse before the morn. 9:59:59.000,9:59:59.000 Every moment dies a man, [br]Every moment one is born." 9:59:59.000,9:59:59.000 So keen statistician was Babbage [br]that he could not contain himself. 9:59:59.000,9:59:59.000 He dashed a letter to Tennyson[br]explaining that because of population growth 9:59:59.000,9:59:59.000 the line should read: 9:59:59.000,9:59:59.000 "Every moment dies a man, [br]And 11/16 is born." 9:59:59.000,9:59:59.000 "I may add that the exact figure is 1.167 9:59:59.000,9:59:59.000 but something must be conceded [br]to the laws of metre." 9:59:59.000,9:59:59.000 In the 19th century scholars all over Europe 9:59:59.000,9:59:59.000 did an amazing work in measuring the societies. 9:59:59.000,9:59:59.000 They hovered up data in almost everything 9:59:59.000,9:59:59.000 but numbers alone don't tell you anything 9:59:59.000,9:59:59.000 you have to analyse them, and that's what makes statistics. 9:59:59.000,9:59:59.000 When the first statisticians began [br]to get to grips with analysing their data 9:59:59.000,9:59:59.000 they seized upon the average, [br]and they took the average of everything. 9:59:59.000,9:59:59.000 What's so great about an average[br] 9:59:59.000,9:59:59.000 is that you can take a whole mass of data and reduce it to a single number. 9:59:59.000,9:59:59.000 Though each of us is unique, [br]our collective lives produce averages 9:59:59.000,9:59:59.000 that characterise whole populations. 9:59:59.000,9:59:59.000 I look to my local newspaper one week 9:59:59.000,9:59:59.000 and saw that a pensioner had accidently [br]put a foot on the accelerator 9:59:59.000,9:59:59.000 and crashed her friend against the wall. 9:59:59.000,9:59:59.000 Devastating, hideous, horrible thing to happen. 9:59:59.000,9:59:59.000 And there was a second one about a young man[br]who didn't have a driving licence 9:59:59.000,9:59:59.000 who was driving a car under the influence[br]of drugs and alcohol 9:59:59.000,9:59:59.000 and crashed into a pedestrian and killed him. 9:59:59.000,9:59:59.000 What is remarkable,[br]absolutely remarkable, 9:59:59.000,9:59:59.000 if you look at the number of people [br]who die each year 9:59:59.000,9:59:59.000 in traffic accidents, [br]it's nearly a constant. 9:59:59.000,9:59:59.000 What? 9:59:59.000,9:59:59.000 All these individual events, [br]somehow when you sum them all up 9:59:59.000,9:59:59.000 it's the same number every year, 9:59:59.000,9:59:59.000 and every year two and a half times[br]as many men die 9:59:59.000,9:59:59.000 in traffic accidents as women,[br]and it's a constant. 9:59:59.000,9:59:59.000 An every year the rate in Belgium is double 9:59:59.000,9:59:59.000 the rate in England, [br]there are these remarkable regularities 9:59:59.000,9:59:59.000 so that these individual particular events[br]sum up into a social phenomenon. 9:59:59.000,9:59:59.000 (Lecture) Let's see what Sweden has done 9:59:59.000,9:59:59.000 we used to boast of fast social progress. 9:59:59.000,9:59:59.000 (Narration) In my lectures, [br]to tell stories about the changing world 9:59:59.000,9:59:59.000 I use averages for entire countries, [br]whether the average for income, 9:59:59.000,9:59:59.000 child mortality, family size or carbon output. 9:59:59.000,9:59:59.000 (Lecture) OK, I give you Singapore, [br]the year I was born. 9:59:59.000,9:59:59.000 Singapore had twice the child mortality of Sweden. 9:59:59.000,9:59:59.000 The most tropical country in the world. [br]A marshland on the Equator. 9:59:59.000,9:59:59.000 And here we go. It took a little time for them to get independence 9:59:59.000,9:59:59.000 but they started to grow their economy, [br]and they made the social investments, 9:59:59.000,9:59:59.000 they got away malaria, [br]they got a magnificient health system 9:59:59.000,9:59:59.000 that beats both UkKs and Sweden's. 9:59:59.000,9:59:59.000 We thought it would never happened [br]but they would win over Sweden! 9:59:59.000,9:59:59.000 But useful as averages are[br]they don't tell you the whole story. 9:59:59.000,9:59:59.000 On average, Swedish people have slightly [br]less than two legs. 9:59:59.000,9:59:59.000 That is because a few people have one leg[br]or no legs, and no one has three legs 9:59:59.000,9:59:59.000 so almost everybody in Sweden[br]has more than the average number of legs. 9:59:59.000,9:59:59.000 The variation in data is just[br]as important as the average. 9:59:59.000,9:59:59.000 But how do you get the handle on variation? 9:59:59.000,9:59:59.000 For this you transform numbers into shapes. 9:59:59.000,9:59:59.000 Let's llok again at the number of adult women [br]in Sweden for different heights. 9:59:59.000,9:59:59.000 Plotting the data as a shape shows us [br]how much their heights vary from the average 9:59:59.000,9:59:59.000 and how wide that variation is. 9:59:59.000,9:59:59.000 The shape a set of data makes [br]is called its distribution. 9:59:59.000,9:59:59.000 (Lecture) This is the income distribution[br]of China 1970 9:59:59.000,9:59:59.000 This is the income distribution[br]of the United States 1970. 9:59:59.000,9:59:59.000 Almost no overlap. And what has happened? 9:59:59.000,9:59:59.000 China is growing. It's not so equal any longer. 9:59:59.000,9:59:59.000 And it's appearing here, [br]overlooking the United States 9:59:59.000,9:59:59.000 almost like a ghost, isn't it? It's scary! 9:59:59.000,9:59:59.000 That statistician who first explored distribution[br] 9:59:59.000,9:59:59.000 discovered one shape that turned up [br]again and again 9:59:59.000,9:59:59.000 the victorian scholar Francis Goldtone[br]was so fascinated 9:59:59.000,9:59:59.000 he built a machine that could reproduce it 9:59:59.000,9:59:59.000 and he found it fitted so many different[br]sets of measurements 9:59:59.000,9:59:59.000 that he named it the Normal Distribution. 9:59:59.000,9:59:59.000 Whether it was people's arm spans, land capacity or even their exam results 9:59:59.000,9:59:59.000 the Normal Distribution shape recurred [br]time and time again. 9:59:59.000,9:59:59.000 And the statisticians soon found[br]many other regular shapes 9:59:59.000,9:59:59.000 each produced by a certain kind of natural or social processes. 9:59:59.000,9:59:59.000 And every statistician has their favourite. 9:59:59.000,9:59:59.000 The Poisson distribution, I think it's my favourite, [br]it's absolute crack. 9:59:59.000,9:59:59.000 The Poisson shape, describes how likely it is [br]that out-of-the-ordinary things will happen. 9:59:59.000,9:59:59.000 Imagine a London bus stop that we know[br]that on average will get three buses an hour. 9:59:59.000,9:59:59.000 We won't always get three buses of course. 9:59:59.000,9:59:59.000 Amazingly the Poisson shape will show us [br]the probability that in any given hour 9:59:59.000,9:59:59.000 will get 4, 5 or 6 buses or no buses at all. 9:59:59.000,9:59:59.000 The exact shape changes with the average 9:59:59.000,9:59:59.000 but whether it is how many people will [br]win the lottery jackpot each week 9:59:59.000,9:59:59.000 or how many people will phone [br]a call centre each minute 9:59:59.000,9:59:59.000 the Poisson shape will give the probabilities. 9:59:59.000,9:59:59.000 The wonderful example where this does apply [br]is in the late 19th century 9:59:59.000,9:59:59.000 was to count each year the number [br]of Prussian officers 9:59:59.000,9:59:59.000 cavalry officers that had be kicked [br]to death by their horses 9:59:59.000,9:59:59.000 Some year there were none, some years one, [br]some years two,... up to seven. 9:59:59.000,9:59:59.000 One particularly bad year. 9:59:59.000,9:59:59.000 But with this distribution, how many years they go, one, two three, four, 9:59:59.000,9:59:59.000 Prussian cavalry officers kicked to death[br]by their horses 9:59:59.000,9:59:59.000 beautifully obbey the Poisson distribution. 9:59:59.000,9:59:59.000 So statisticians use shapes so we wield the patterns in the data 9:59:59.000,9:59:59.000 but we also use images of all kinds to communicate statistics to a wider public 9:59:59.000,9:59:59.000 because if the story in the numbers is told by a beautiful and clever image 9:59:59.000,9:59:59.000 then everyone understands. 9:59:59.000,9:59:59.000 Of the pioneers of statiscal graphics, my favourite is Florence Nightingale. 9:59:59.000,9:59:59.000 There are not many people who realise that actually she was known as a passionate statistician 9:59:59.000,9:59:59.000 and not just the Lady of the Lamp. 9:59:59.000,9:59:59.000 She said that to understand God's thoughts we must study statistics 9:59:59.000,9:59:59.000 for these are the measure of His purpose. 9:59:59.000,9:59:59.000 Statistics must reserve a religious studio moral imperative. 9:59:59.000,9:59:59.000 When Florence was nine years old, [br]she started collecting data. 9:59:59.000,9:59:59.000 Her data was different fruits and vegetables she found. 9:59:59.000,9:59:59.000 Put them into different tables, [br]trying to organise them in some standard form, 9:59:59.000,9:59:59.000 so we have one of the Nightgale's first [br]statistical tables at the age of nine. 9:59:59.000,9:59:59.000 In the mid-1850s, Florence Nightingale went to Crimea 9:59:59.000,9:59:59.000 to care for British casualties at war. 9:59:59.000,9:59:59.000 She was horrified by what she discovered. 9:59:59.000,9:59:59.000 For all the soldiers being blown to bits on the battlefield 9:59:59.000,9:59:59.000 there were many many more soldiers [br]dying from diseases 9:59:59.000,9:59:59.000 caught in the army's filthy hospitals. 9:59:59.000,9:59:59.000 So Florence Nightingale bagan counting the dead. 9:59:59.000,9:59:59.000 For two years she recorded mortality data [br]in meticulous detail. 9:59:59.000,9:59:59.000 When the war was over, [br]she persuaded the government 9:59:59.000,9:59:59.000 to set up a Royal Comission of Enquiry. 9:59:59.000,9:59:59.000 And gathered her data in a devastating report. 9:59:59.000,9:59:59.000 What has amended her place in the statistically[br]history books is the graphics she used. 9:59:59.000,9:59:59.000 And one in particular, the Polar Area Graph. 9:59:59.000,9:59:59.000 For each month of the war,[br]a huge blue wedge represented the soldiers 9:59:59.000,9:59:59.000 who had died of preventable diseases. 9:59:59.000,9:59:59.000 The much smaller red wedges [br]were deaths from wounds, 9:59:59.000,9:59:59.000 and the black wedges deaths [br]from accidents and other causes. 9:59:59.000,9:59:59.000 Nightingale graphics were so clear, [br]they were impossible to ignore. 9:59:59.000,9:59:59.000 The usual thing around Florence Nightingale's time 9:59:59.000,9:59:59.000 was just to produce tables and tables of figures.[br]Absolutely tedious stuff. 9:59:59.000,9:59:59.000 Unless you are a dedicated statistician, [br]it's quite difficult to spot the patterns naturally. 9:59:59.000,9:59:59.000 But visualisations tell a story. [br]They tell a story immediately. 9:59:59.000,9:59:59.000 The use of colour, the use of shape, [br]can really tell a powerful story. 9:59:59.000,9:59:59.000 And these days, we can make things move as well. 9:59:59.000,9:59:59.000 Florence Nightingale would've loved to play with it, 9:59:59.000,9:59:59.000 she would've produced wonderful animations, [br]I'm absolutely certain about it. 9:59:59.000,9:59:59.000 Today, a hundred and fifty years on, [br] 9:59:59.000,9:59:59.000 Nightingale's graphics are rightly [br]regarded as a classic. 9:59:59.000,9:59:59.000 They led to a revolution in nursing and health care, [br]in hygiene in hospitals worldwide. 9:59:59.000,9:59:59.000 We've saved innumerable lives. 9:59:59.000,9:59:59.000 Statistical graphics has become[br]an art of its very own. 9:59:59.000,9:59:59.000 Led by designers who are passionate [br]about visualising data. 9:59:59.000,9:59:59.000 This is the Billion Pound O Gram. 9:59:59.000,9:59:59.000 This image arouse out of the frustration [br]with the reporting 9:59:59.000,9:59:59.000 of billion-pounds amounts in the media. 9:59:59.000,9:59:59.000 500 trillion pounds for this war, [br]50 million pounds for this hospital, 9:59:59.000,9:59:59.000 this does not make sense,[br]these figures are too enormous to get your mind around. 9:59:59.000,9:59:59.000 So I squailed to this data from various news sources[br]and created this diagram 9:59:59.000,9:59:59.000 so the squares here are scaled[br]according the the billion-pound amounts. 9:59:59.000,9:59:59.000 When you see numbers visualised like this,[br] 9:59:59.000,9:59:59.000 you start to have a different [br]kind of relationship with them. 9:59:59.000,9:59:59.000 You can see patterns, see the scale of them. 9:59:59.000,9:59:59.000 Here, this little square, 37 billion, [br]this was the predicted cost of the Iraq war in 2003. 9:59:59.000,9:59:59.000 As you can see it has grown exponentially[br]over the last few years 9:59:59.000,9:59:59.000 to the total cost of about 2,500 billion. 9:59:59.000,9:59:59.000 It's funny because when you visualise statistics [br]like this, you undestand them. 9:59:59.000,9:59:59.000 And when you understand them,[br]you can put things into perspective. 9:59:59.000,9:59:59.000 Visualisation is right at the heart of my own work too. 9:59:59.000,9:59:59.000 I teach Global Health. 9:59:59.000,9:59:59.000 I know that having the data is not enough, 9:59:59.000,9:59:59.000 I have to show it in ways people [br]both enjoy and undestand. 9:59:59.000,9:59:59.000 Now I'm going to try something [br]I've never done before. 9:59:59.000,9:59:59.000 Animating the data in real space. 9:59:59.000,9:59:59.000 With a bit of technical assistance [br]from the crew. 9:59:59.000,9:59:59.000 So here we go! 9:59:59.000,9:59:59.000 First an axis for health, [br]life expectancy from 25 years to 75 years. 9:59:59.000,9:59:59.000 Down here an axis for wealth, [br]income per person, $400, $4,000 and $40,000. 9:59:59.000,9:59:59.000 So down here is poor and sick.[br]And up here is rich and healthy. 9:59:59.000,9:59:59.000 Now I'm going to show you the world [br]200 years ago, in 1810. 9:59:59.000,9:59:59.000 Here come all the countries: [br]Europe brown, Asia red, 9:59:59.000,9:59:59.000 Middle East green, Africa South-of-Sahara blue, [br]and America is yellow. 9:59:59.000,9:59:59.000 And the size of the country bubble [br]shows the size of the population. 9:59:59.000,9:59:59.000 And in 1810 it was pretty crowded down there, isn't it? 9:59:59.000,9:59:59.000 All countries were sick and poor, [br]life expectancy would be below 40 in all countries. 9:59:59.000,9:59:59.000 Only the UK and the Netherlands [br]were slightly better off, but not much. 9:59:59.000,9:59:59.000 And now, I'll start the world! 9:59:59.000,9:59:59.000 The Industrial Revolution makes countries in Europe and elsewhere move away from the rest. 9:59:59.000,9:59:59.000 But the colonised countries in Asia and Africa [br]are stuck down there. 9:59:59.000,9:59:59.000 Eventually the Western countries [br]get healthier and healthier. 9:59:59.000,9:59:59.000 Now we slow down to see the impact[br]of the First World War and the Spanish Flu Epidemy. 9:59:59.000,9:59:59.000 What a catastrophe! 9:59:59.000,9:59:59.000 Now I'll speed up through the 1920s and 1930s 9:59:59.000,9:59:59.000 and spite of the Great Depression, Western countries fueled on towards greater wealth and health. 9:59:59.000,9:59:59.000 Japan and some others try to follow[br]but most countries stay down here. 9:59:59.000,9:59:59.000 After the tragedies of the Second World War 9:59:59.000,9:59:59.000 we stop a bit to look at the world in 1948. 9:59:59.000,9:59:59.000 1948 was a great year, the war was over,[br]Sweden topped the medal table at the Winter Olympics, 9:59:59.000,9:59:59.000 and I was born, but the differences between [br]the countries of the world was wider than ever. 9:59:59.000,9:59:59.000 United States was in the front, [br]Japan was catching up, Brasil was way behind, 9:59:59.000,9:59:59.000 Iran was getting a little richer from oil, [br]but still had short lives. 9:59:59.000,9:59:59.000 The Asian giants, China, India,[br]Pakistan, Bangladesh and Indonesia, 9:59:59.000,9:59:59.000 they were still poor and sit down here. 9:59:59.000,9:59:59.000 But look what is about to happen. In my lifetime,[br]former colonies gained independence 9:59:59.000,9:59:59.000 and finally they started to get healthier,[br]and healthier, and healthier. 9:59:59.000,9:59:59.000 And in the 1970s, [br]countries in Asia and Latin America 9:59:59.000,9:59:59.000 started to catch up with the Western countries. 9:59:59.000,9:59:59.000 They became the emerging economies. 9:59:59.000,9:59:59.000 Some in Africa follow, some in Africa [br]are stuck in civil wars, and others are hit by HIV. 9:59:59.000,9:59:59.000 And now we can see the world today, [br]in the most up-to-date statistics. 9:59:59.000,9:59:59.000 Most people today live in the middle, 9:59:59.000,9:59:59.000 but here are huge differences at the same time[br] 9:59:59.000,9:59:59.000 between the best of countries [br]and the worst of countries 9:59:59.000,9:59:59.000 and there are also huge inequalities within countries. 9:59:59.000,9:59:59.000 These bubbles show country averages,[br]but I can split them. 9:59:59.000,9:59:59.000 Take China, I can split it into provinces. 9:59:59.000,9:59:59.000 There goes Shanghai, [br]it has the same health and wealth as Italy today. 9:59:59.000,9:59:59.000 And then there's the poor inland province of Guizhou. It's like Pakistan. 9:59:59.000,9:59:59.000 And if I split it further, [br]the rural parts are like Ghana in Africa. 9:59:59.000,9:59:59.000 And yet, despite the enormous disparities today,[br]we have seen 200 years of remarkable progress. 9:59:59.000,9:59:59.000 That huge historical gap between [br]the West and the rest is now closing. 9:59:59.000,9:59:59.000 We have become an entirely new converging world. 9:59:59.000,9:59:59.000 And I see a clear trend into the future,[br]with aid, trade, green technology and peace. 9:59:59.000,9:59:59.000 It's fully possible that everyone [br]can make it to the healthy-wealthy corner. 9:59:59.000,9:59:59.000 What you've just seen in the last few minutes[br]is a story of 200 countries 9:59:59.000,9:59:59.000 shown over 200 years and beyond. [br]It involved plotting 120,000 numbers. 9:59:59.000,9:59:59.000 Pretty neat, eh? 9:59:59.000,9:59:59.000 With statistics we can start to see things [br]as they really are. 9:59:59.000,9:59:59.000 From tables of data, to averages, [br]distributions and visualisations, 9:59:59.000,9:59:59.000 statistics gives us a clear description of the world. 9:59:59.000,9:59:59.000 But with statistics we can not only [br]discover what is happening 9:59:59.000,9:59:59.000 but also explore why, by using [br]the powerful analytical method of correlation. 9:59:59.000,9:59:59.000 Just looking at one thing at a time[br]doesn't tell you very much. 9:59:59.000,9:59:59.000 You have to look at the relationships between things.[br] 9:59:59.000,9:59:59.000 How they change. How they vary together.[br]That's what correlation is about. 9:59:59.000,9:59:59.000 That's how we start to understand[br]the processes that are really going on 9:59:59.000,9:59:59.000 in the world and in socierty. 9:59:59.000,9:59:59.000 Most of us would recognise today that crime[br]correlates to poverty, 9:59:59.000,9:59:59.000 that infection correlates to poor sanitasion, 9:59:59.000,9:59:59.000 and that knowledge of statistics correlates [br]to being great at dancing. 9:59:59.000,9:59:59.000 Correlations can be very tricky. 9:59:59.000,9:59:59.000 I've got a joke about silly correlations. 9:59:59.000,9:59:59.000 This was this American [br]who was afraid of heart attack. 9:59:59.000,9:59:59.000 He found out that the Japanese ate very little fat,[br]and almost didn't drink wine, 9:59:59.000,9:59:59.000 and have much less heart attacks than the American. 9:59:59.000,9:59:59.000 But on the other hand, he found out that the French[br]eat as much fat as the Americans 9:59:59.000,9:59:59.000 and they drink much more wine, but they also have less heart attacks. 9:59:59.000,9:59:59.000 so he concluded that what kills you [br]is speaking English. 9:59:59.000,9:59:59.000 The best example of [br]a really ground-breaking correlation 9:59:59.000,9:59:59.000 was the link that was established in the 1950s[br]between smoking and lung cancer. 9:59:59.000,9:59:59.000 Not long after the Second World War,[br]a British doctor, Richard Doll, 9:59:59.000,9:59:59.000 investigated lung cancer patients[br]in twenty London hospitals, 9:59:59.000,9:59:59.000 and he became certain that [br]the only thing they had in common was smoking 9:59:59.000,9:59:59.000 so certain that he stopped smoking himself. 9:59:59.000,9:59:59.000 But other people weren't so sure. 9:59:59.000,9:59:59.000 Lots of the discussion of early data [br]linking smoking and lung cancer 9:59:59.000,9:59:59.000 it can't be smoking, surely, that thing [br]we've done all our lives, that can't be bad for you. 9:59:59.000,9:59:59.000 Maybe it's genes, maybe people [br]who are genetically predisposed to get lung cancer 9:59:59.000,9:59:59.000 are also genetically predisposed to smoke. 9:59:59.000,9:59:59.000 Maybe it's not the smoking, [br]maybe it's air pollution, 9:59:59.000,9:59:59.000 that smokers and somehow more exposed to air pollution than non-smokers. 9:59:59.000,9:59:59.000 Maybe it's not smoking, maybe it's poverty. 9:59:59.000,9:59:59.000 So now we have three possible explanations [br]apart from chance. 9:59:59.000,9:59:59.000 To verify his correlation did imply cause and effect 9:59:59.000,9:59:59.000 Richard Doll created [br]the biggest statistical study of smoking yet 9:59:59.000,9:59:59.000 He began tracking the lives of 40,000 British doctors 9:59:59.000,9:59:59.000 some of whom smoked, some of whom didn't. 9:59:59.000,9:59:59.000 And gathered enough data to correlate [br]the amount of doctors who smoked 9:59:59.000,9:59:59.000 with their likelihood of getting cancer. 9:59:59.000,9:59:59.000 Eventually, he did not only show a correlation [br]between smoking and lung cancer 9:59:59.000,9:59:59.000 but also a correlation between stopping smoking [br]and reducing the risk. 9:59:59.000,9:59:59.000 This was science at its best. 9:59:59.000,9:59:59.000 What correlations do not replace[br]is human thought. 9:59:59.000,9:59:59.000 We could think about what it means. 9:59:59.000,9:59:59.000 What a good scientist does [br]if he comes up with a correlation 9:59:59.000,9:59:59.000 is try as hard as he or she possibly can [br]to disprove it 9:59:59.000,9:59:59.000 to break it down, to get rid of it, [br]to try to refute it, 9:59:59.000,9:59:59.000 and if it withstands all those efforts [br]at demolishing it, and it still standing out, 9:59:59.000,9:59:59.000 then we might really have something here. 9:59:59.000,9:59:59.000 However brilliants the scientists, [br]data is still the oxygen of science. 9:59:59.000,9:59:59.000 The good news is that the more we have, [br]the more correlations we'll find, 9:59:59.000,9:59:59.000 the more theories we'll test, [br]and the more discoveries we are likely to make. 9:59:59.000,9:59:59.000 And history shows how our total sum of information [br]grows in huge leaps 9:59:59.000,9:59:59.000 as we develop new technologies. 9:59:59.000,9:59:59.000 The invention of the printing press kicked off [br]the first data and information explosion 9:59:59.000,9:59:59.000 If you piled up all the books that have been printed[br]by the year 1700 9:59:59.000,9:59:59.000 they would make sixty stacks,[br]each as high as Mount Everest. 9:59:59.000,9:59:59.000 Then, starting in the 19th century,[br]there came a second information revolution. 9:59:59.000,9:59:59.000 With the telegraph, gramophone, camera, [br]and later radio and TV. 9:59:59.000,9:59:59.000 The total amount of information exploded. 9:59:59.000,9:59:59.000 And by the 1950s the information available to us all [br]had multiplied six thousend times. 9:59:59.000,9:59:59.000 Then, thanks to the computer,[br]and later the Internet, we went digital, 9:59:59.000,9:59:59.000 and the amount of data we have now, [br]is unimaginably vast. 9:59:59.000,9:59:59.000 A single letter printed in a book [br]is the equivalent to a byte of data. 9:59:59.000,9:59:59.000 A single page [br]equals a kilobyte or two. 9:59:59.000,9:59:59.000 Five megabytes is enough [br]for the complete works of Shakespeare. 9:59:59.000,9:59:59.000 10 gigabytes, that's a DVD movie. 9:59:59.000,9:59:59.000 2 terabytes is the tens of millions of photos [br]added to Facebook everyday. 9:59:59.000,9:59:59.000 10 petabytes is the data recorded every second[br]by the world's largest particle accelerator, 9:59:59.000,9:59:59.000 so much only a tiny fraction is kept. 9:59:59.000,9:59:59.000 6 exabytes is what you'd have if you sequenced [br]the genomes of every single person on Earth. 9:59:59.000,9:59:59.000 But really, that's nothing. [br]In 2009, the Internet added up to 600 exabytes, 9:59:59.000,9:59:59.000 and in 2010, in just one year, that will double to more than one zettabyte. 9:59:59.000,9:59:59.000 But in the real world, [br]if we turned all this data into print 9:59:59.000,9:59:59.000 it would make ninety stacks of books,[br]each reaching from here all the way to the Sun. 9:59:59.000,9:59:59.000 The data deluge is staggering. [br]But with today's computers and statistics, 9:59:59.000,9:59:59.000 I'm confident we can handle it. 9:59:59.000,9:59:59.000 When it comes to all the data on the Internet, 9:59:59.000,9:59:59.000 the powerhouse of statistical analysis[br]is the Sillicon Valley giant Google. 9:59:59.000,9:59:59.000 The average person over their lifetime 9:59:59.000,9:59:59.000 is exposed to about a hundred million words[br]of conversation. 9:59:59.000,9:59:59.000 So if you multiply that [br]by the six billion people on the planet 9:59:59.000,9:59:59.000 that amount of words is equal to the amount of words 9:59:59.000,9:59:59.000 that Google has available at any one instant of time. 9:59:59.000,9:59:59.000 Google's computers hoover up and file away[br] 9:59:59.000,9:59:59.000 every document, web page [br]and image they can find. 9:59:59.000,9:59:59.000 Then they hunt for patterns and correlations[br]in all this data 9:59:59.000,9:59:59.000 doing statistics on a massive scale. 9:59:59.000,9:59:59.000 And for me, Google has one project[br]that is particularly exciting: 9:59:59.000,9:59:59.000 statistical language translation. 9:59:59.000,9:59:59.000 If you do want to provide access [br]to all the web's information 9:59:59.000,9:59:59.000 no matter what language is spoken. 9:59:59.000,9:59:59.000 There's so much information on the Internet, [br]you can not hope to tranlate it all by hand 9:59:59.000,9:59:59.000 into every possible language, we figured [br]we have to be able to do machine translation. 9:59:59.000,9:59:59.000 In the past, programmers tried to teach their computers to see each language as a set of grammatical rules. 9:59:59.000,9:59:59.000 Much like languages are taught at school. 9:59:59.000,9:59:59.000 But this didn't work, because no set of rules[br]could capture language in all its subtlety and ambiguity, 9:59:59.000,9:59:59.000 Having eaten out lunch, [br]the coach departed. 9:59:59.000,9:59:59.000 That's obviously incorrect. Written like that,[br]it would imply that the coach has eaten the lunch. 9:59:59.000,9:59:59.000 It would be far better to say: Having eaten our lunch,[br]we departed in the coach. 9:59:59.000,9:59:59.000 Those rules are helpful, [br]they are useful most of the time, 9:59:59.000,9:59:59.000 but they don't turn out to be true [br]all the time. 9:59:59.000,9:59:59.000 And the insight of using [br]statistical machine translation[br] 9:59:59.000,9:59:59.000 is saying: if we have all these exceptions anyways, maybe you can get by without having any rules, 9:59:59.000,9:59:59.000 maybe we can treat everything as an exception,[br]and that's essentially what we've done. 9:59:59.000,9:59:59.000 What the computer is doing [br]when it's learning how to translate 9:59:59.000,9:59:59.000 is to learn correlations between words[br]and between phrases 9:59:59.000,9:59:59.000 so we feed the system [br]very large amounts of data 9:59:59.000,9:59:59.000 and the the system sees if a certain word or phrase[br]correlates very often to the other language. 9:59:59.000,9:59:59.000 Google's website currently offers translation between any of 57 different languages. 9:59:59.000,9:59:59.000 It does this purely statistically,having correlated [br]the huge collection of multilingual texts. 9:59:59.000,9:59:59.000 The people who built he system[br]don't need to know Chinese 9:59:59.000,9:59:59.000 in order to build the Chinese system.[br]They dont need to know Arabic. 9:59:59.000,9:59:59.000 The expertise that is needed is basically knowledge of statistics, of computer science, 9:59:59.000,9:59:59.000 of infrastructure, 9:59:59.000,9:59:59.000 to build these very large computer systems we are building for doing that. 9:59:59.000,9:59:59.000 I hooked up with Google from my office in Stockholm,[br]to try the translator by myself. 9:59:59.000,9:59:59.000 I will type some Swedish sentences. 9:59:59.000,9:59:59.000 (Types in Swedish) 9:59:59.000,9:59:59.000 (Reads on the screen) Sweden's finance minister [br]has a ponytail and a gold ring in your ear. 9:59:59.000,9:59:59.000 It's almost exactly correct, it's amazing. 9:59:59.000,9:59:59.000 He comes from the conservative party, [br]that's the kind of Sweden we have today. 9:59:59.000,9:59:59.000 I will type one more sentence. 9:59:59.000,9:59:59.000 In his same-sex parnertships has Stockholm's [br]new bishop and his partners a three-year son. 9:59:59.000,9:59:59.000 It's almost perfect, [br]there's one important thing, it's "her". 9:59:59.000,9:59:59.000 It's a lesbian partnership. 9:59:59.000,9:59:59.000 OK, those kinds of words like "her"[br]are one of the challenges in translation, 9:59:59.000,9:59:59.000 to get those right. 9:59:59.000,9:59:59.000 When it comes to bishops, [br]one can excuse it. 9:59:59.000,9:59:59.000 Right, I think that more often than not [br]it would be probably a "his". 9:59:59.000,9:59:59.000 I will write one more sentence. [br](Reads aloud in Swedish) 9:59:59.000,9:59:59.000 When Sweden is taking part in Olympic gold, [br]is not to win but to beat Norway. 9:59:59.000,9:59:59.000 But they are very good in Winter Olympics,[br]so we can't make it, but we are trying. 9:59:59.000,9:59:59.000 Very good, very good. 9:59:59.000,9:59:59.000 This is absolutely amazing, 9:59:59.000,9:59:59.000 and I'm impressed that it picked up [br]words like "same-sex partnerships" 9:59:59.000,9:59:59.000 which are very due to the language. 9:59:59.000,9:59:59.000 The translator is good, but if it succeeds,[br]what will be next, that'll be remarkable. 9:59:59.000,9:59:59.000 One of the exciting possibilities is combining[br]the machine translation technology 9:59:59.000,9:59:59.000 [br]with the speech recognition technology. 9:59:59.000,9:59:59.000 Both of these are statistically neutre. 9:59:59.000,9:59:59.000 The machine translation relies on the statistics [br]of mapping from one language to another, 9:59:59.000,9:59:59.000 and similarly speech recognition relies on the statistics[br]of mapping from a sound form to the words. 9:59:59.000,9:59:59.000 When we put them together, [br]now we have the capability 9:59:59.000,9:59:59.000 of having instant conversations between two people who don't speak a common language. 9:59:59.000,9:59:59.000 I can talk to you in my language, [br]you hear me in your language, 9:59:59.000,9:59:59.000 and you can answer back in real time,[br]we can make that translation, 9:59:59.000,9:59:59.000 we can bring people together [br]and allow them to speak. 9:59:59.000,9:59:59.000 The Internet is just one of many technologies[br]created to gather massives amount of data. 9:59:59.000,9:59:59.000 Scientists studying our Earth[br]and our environment 9:59:59.000,9:59:59.000 now use an incredible range of instruments[br]to measure the processes of our planet. 9:59:59.000,9:59:59.000 All around us our sensors are continously measuring[br]temperature, water flow and ocean currents. 9:59:59.000,9:59:59.000 High in orbit our satellite is busy imaging cloud formations, forest growth and snow cover. 9:59:59.000,9:59:59.000 Scientists speak of instrumenting the Earth. 9:59:59.000,9:59:59.000 And pointing up to the skies above, 9:59:59.000,9:59:59.000 our powerful new telescopes are mapping the Universe. 9:59:59.000,9:59:59.000 What's happening in astronomy, [br]is tipically how profoundly this torrent of data 9:59:59.000,9:59:59.000 is transforming science. 9:59:59.000,9:59:59.000 Astronomers are now addressing [br]many enduring misteries of the cosmos 9:59:59.000,9:59:59.000 by applying statistical methods[br]to all this new data. 9:59:59.000,9:59:59.000 The galaxy is a very big place [br]and it has billions of starts in it 9:59:59.000,9:59:59.000 so to put toghether a coherent picture [br]of the whole galaxy requires 9:59:59.000,9:59:59.000 having enourmous amounts of data, [br]and before you can do a large sky survey 9:59:59.000,9:59:59.000 with sensitive digital detectors, [br]that you can map many stars at once, 9:59:59.000,9:59:59.000 it's very difficult to gather enough data [br]of enough of the galaxy. 9:59:59.000,9:59:59.000 In the past, large surveys of the night sky[br]had to be done 9:59:59.000,9:59:59.000 by exposing thousands [br]of large photographic plates, 9:59:59.000,9:59:59.000 but these surveys could take 25 years [br]or more to complete. 9:59:59.000,9:59:59.000 Then, in the 1990s, came digital astronomy, 9:59:59.000,9:59:59.000 and a huge increase in both the amount[br]and the accesibility of data. 9:59:59.000,9:59:59.000 The Sloan Sky Survey is the world's biggest yet 9:59:59.000,9:59:59.000 using a massive digital sensor mounted 9:59:59.000,9:59:59.000 on the back of a custom built telescope in New Mexico. 9:59:59.000,9:59:59.000 It's scanned the sky night after night for eight years 9:59:59.000,9:59:59.000 building up a composite picture [br]in unprecedented resolution. 9:59:59.000,9:59:59.000 The Sloan's is some of the best deepest survey data 9:59:59.000,9:59:59.000 we have in astronomy, 9:59:59.000,9:59:59.000 both in our galaxy and galaxies away from ours. 9:59:59.000,9:59:59.000 All the Sloan data is on the Internet 9:59:59.000,9:59:59.000 and with it astronomers have identified 9:59:59.000,9:59:59.000 millions of hidden unknown stars and galaxies. 9:59:59.000,9:59:59.000 They also comb the database for statistical patterns 9:59:59.000,9:59:59.000 which will prove, disprove or suggest new theories. 9:59:59.000,9:59:59.000 So we have this idea that galaxies grow 9:59:59.000,9:59:59.000 they become large galaxies 9:59:59.000,9:59:59.000 like the one we live in, the Milky Way. 9:59:59.000,9:59:59.000 Not all at once, not smoothly 9:59:59.000,9:59:59.000 but by continously incorporating 9:59:59.000,9:59:59.000 cannibalising smaller galaxies 9:59:59.000,9:59:59.000 they dissolve them and become [br]part of the bigger galaxy 9:59:59.000,9:59:59.000 It's a startling idea 9:59:59.000,9:59:59.000 and in the Sloan data there's the evidence to support it. 9:59:59.000,9:59:59.000 Groups of starts that came from cannibalised galaxies 9:59:59.000,9:59:59.000 stand out in the Sloan data statistically[br]different from other stars. 9:59:59.000,9:59:59.000 because they move at a different velocity. 9:59:59.000,9:59:59.000 Each big spike of one of these distribution graphs 9:59:59.000,9:59:59.000 means professor Rockossi has found a group of stars 9:59:59.000,9:59:59.000 all travelling in a different way to the rest. 9:59:59.000,9:59:59.000 They are the telltale patterns she's looking for. 9:59:59.000,9:59:59.000 The evidence is accumulating that in fact 9:59:59.000,9:59:59.000 this really is how galaxies grow 9:59:59.000,9:59:59.000 or an important way of how galaxies grow 9:59:59.000,9:59:59.000 this is important to understand how galaxies form 9:59:59.000,9:59:59.000 not only ours but every galaxy. 9:59:59.000,9:59:59.000 The more data there is [br]the more discoveries can be made 9:59:59.000,9:59:59.000 and the technology is getting better all the time. 9:59:59.000,9:59:59.000 The next big survey telescope starts its work in 2015. 9:59:59.000,9:59:59.000 It will leave Sloan in the dust. 9:59:59.000,9:59:59.000 Sloan has taken 8 eight years [br]to cover one quarter of the nightsky. 9:59:59.000,9:59:59.000 The new telescope will scan the entire sky[br]in even greater resolution 9:59:59.000,9:59:59.000 every three days. 9:59:59.000,9:59:59.000 The vast amounts of data we have today 9:59:59.000,9:59:59.000 allows researchers in all sorts of fields 9:59:59.000,9:59:59.000 to test their theories in a previously unimaginable scale 9:59:59.000,9:59:59.000 but it may even change the fundamental way [br]science is done. 9:59:59.000,9:59:59.000 With the power of todays' computers[br]applied to all this data 9:59:59.000,9:59:59.000 the machines might be able to guide the researchers. 9:59:59.000,9:59:59.000 There is a profoundly important, [br]one of the most significant points in science 9:59:59.000,9:59:59.000 certainly one of the most exciting 9:59:59.000,9:59:59.000 the potential to transform not only [br]how scientists do science 9:59:59.000,9:59:59.000 but what science is possibly. 9:59:59.000,9:59:59.000 What will power that transformation [br]of how science is done 9:59:59.000,9:59:59.000 is going to be computation. 9:59:59.000,9:59:59.000 Many of the dynamics of the natual world 9:59:59.000,9:59:59.000 like the interplay [br]between the rainforest and the atmosphere 9:59:59.000,9:59:59.000 are so complex, that we don't yet[br]really understand. 9:59:59.000,9:59:59.000 But now computers are generating [br]tens of thousands of simulations 9:59:59.000,9:59:59.000 of how these biological systems might work. 9:59:59.000,9:59:59.000 Is like creating thousands of [br]hypothetical parellel worlds. 9:59:59.000,9:59:59.000 Each of these simulations is analysed with statistics 9:59:59.000,9:59:59.000 to see if any are a good match[br]of what is observed in each. 9:59:59.000,9:59:59.000 The computers can now automatically generate, 9:59:59.000,9:59:59.000 test and discard hypothesis [br]with scarcely human insight. 9:59:59.000,9:59:59.000 This new application statistics will become 9:59:59.000,9:59:59.000 absolutely vital for the future of science. 9:59:59.000,9:59:59.000 It's creating a new paradigm in the way we do science 9:59:59.000,9:59:59.000 which is characterised as data-centric or data-driven 9:59:59.000,9:59:59.000 rather than hypothesis- or experiment-driven. 9:59:59.000,9:59:59.000 It's an exciting time in terms of science,[br]computation and statistics. 9:59:59.000,9:59:59.000 If all this sounds a bit abstract to you 9:59:59.000,9:59:59.000 how about one final frontier? 9:59:59.000,9:59:59.000 Could statistics make sense of your feelings? 9:59:59.000,9:59:59.000 In California, (where else!), one computer scientist 9:59:59.000,9:59:59.000 is harvesting the Internet to try to define the patterns 9:59:59.000,9:59:59.000 of our innermost thoughts and emotions. 9:59:59.000,9:59:59.000 This is the Madness Movement 9:59:59.000,9:59:59.000 it represents a skyscrapper's view of the world. 9:59:59.000,9:59:59.000 Each brightly coloured dot is an individual feeling 9:59:59.000,9:59:59.000 expressed by someone out there in a blog or a tweet 9:59:59.000,9:59:59.000 and when you click on the dot 9:59:59.000,9:59:59.000 it explodes to reveal [br]the underlying feeling of that person. 9:59:59.000,9:59:59.000 This is what people say they're feeling today: 9:59:59.000,9:59:59.000 better 9:59:59.000,9:59:59.000 safe 9:59:59.000,9:59:59.000 crappy 9:59:59.000,9:59:59.000 well 9:59:59.000,9:59:59.000 pretty 9:59:59.000,9:59:59.000 special 9:59:59.000,9:59:59.000 sorry 9:59:59.000,9:59:59.000 alone 9:59:59.000,9:59:59.000 Every minute WeFeelFine crosses the world's blogs 9:59:59.000,9:59:59.000 takes all the sentences that start [br]with the words "I feel" or "I'm feeling" 9:59:59.000,9:59:59.000 and push them into a database. 9:59:59.000,9:59:59.000 We collect all the feelings [br]and we count the most common 9:59:59.000,9:59:59.000 better 9:59:59.000,9:59:59.000 bad 9:59:59.000,9:59:59.000 good 9:59:59.000,9:59:59.000 right 9:59:59.000,9:59:59.000 guilty 9:59:59.000,9:59:59.000 sick 9:59:59.000,9:59:59.000 the same 9:59:59.000,9:59:59.000 like shit 9:59:59.000,9:59:59.000 sorry 9:59:59.000,9:59:59.000 well 9:59:59.000,9:59:59.000 We can take a look at any one feeling and analyse it. 9:59:59.000,9:59:59.000 Right now a lot of people are feeling happy. 9:59:59.000,9:59:59.000 We can take a look at these people, [br]and break them down by age, gender or location. 9:59:59.000,9:59:59.000 Since bloggers have public profiles,[br]we have that information 9:59:59.000,9:59:59.000 and we can ask questions like, [br]"Are women happier than men?" 9:59:59.000,9:59:59.000 or "Is England happier[br]than the United States?" 9:59:59.000,9:59:59.000 We find that as people get older, they get happier. 9:59:59.000,9:59:59.000 For younger people, [br]happiness associates with excitement 9:59:59.000,9:59:59.000 whereas older people associate happiness[br]more with peacefulness. 9:59:59.000,9:59:59.000 We also find than women feel loved [br]more often than men, 9:59:59.000,9:59:59.000 but also more guilty. 9:59:59.000,9:59:59.000 While men feel good more often than women,[br]but also more alone. 9:59:59.000,9:59:59.000 As people live more and more of their lives online 9:59:59.000,9:59:59.000 they leave behind digital traces 9:59:59.000,9:59:59.000 with which we can statistically analyse 9:59:59.000,9:59:59.000 what it means to be human. 9:59:59.000,9:59:59.000 Where does all this leave us? 9:59:59.000,9:59:59.000 We generate unimaginable quantities of data 9:59:59.000,9:59:59.000 About everything you can think of 9:59:59.000,9:59:59.000 and we analyse it to reveal the patterns. 9:59:59.000,9:59:59.000 Now not only experts but all of us can understand 9:59:59.000,9:59:59.000 the stories in the numbers. 9:59:59.000,9:59:59.000 Instead of being led astray by prejudice 9:59:59.000,9:59:59.000 with statistics at our fingertips, our eyes can be open 9:59:59.000,9:59:59.000 for a facts-based view of the world. 9:59:59.000,9:59:59.000 More than ever before we can become [br]authors of our own destiny. 9:59:59.000,9:59:59.000 And that's pretty exciting isn't it? 9:59:59.000,9:59:59.000 (Music)