Statistical Data Quotes

More data means more information, but it also means more false information.

Above all else show the data.

If the statistics are boring, then you've got the wrong numbers.

1. So, disturbed kids are taking guns to school and killing teachers and classmates. We better make sure kids can’t get guns. 2. So, disturbed kids are taking guns to school and killing teachers and classmates. We better find out what’s making these kids want to kill, fix that, and then they won’t want to use guns to kill teachers and classmates. See what I did there? Which statement makes more sense? Don’t bring up politics. Don’t refer to statistical data. Don’t nervously look at your cell phone. Just read the two statements and be honest with yourself. We can do better. We’re smarter than this. WAKE UP.

It’s easy to lie with statistics, but it’s hard to tell the truth without them.

He became another data point in the American experiment of self-government, an experiment statistically skewed from the outset, because it wasn't the people with sociable genes who fled the crowded Old World for the new continent; it was the people who didn't get along well with others.

Faith doesn't rely on odds or statistical data. God only requires that we have faith; the rest is up to him.

Much of what we think of as cultural differences turn out to be differences in income.

The government are very keen on amassing statistics. They collect them, add them, raise them to the nth power, take the cube root and prepare wonderful diagrams. But you must never forget that every one of these figures comes in the first instance from the village watchman, who just puts down what he damn pleases.

Allowing artist-illustrators to control the design and content of statistical graphics is almost like allowing typographers to control the content, style, and editing of prose.

To clarify, *add* data.

In the business people with expertise, experience and evidence will make more profitable decisions than people with instinct, intuition and imagination.

The official report was a collection of cold, hard data, an objective "after-action report" that would allow future generations to study the events of that apocalyptic decade without being influenced by the "human factor." But isn't the human factor what connects us so deeply to our past? Will future generations care as much for chronologies and casualty statistics as they would for the personal accounts of individuals not so different from themeslves? By excluding the human factor, aren't we risking the kind of personal detachment from a history that may, heaven forbid, lead us one day to repeat it?

When moral posturing is replaced by an honest assessment of the data, the result is often a new, surprising insight.

By the time your perfect information has been gathered, the world has moved on.

Ten rules of thumb are still a lot for anyone to remember, so perhaps I should try to make things simpler. I realize that these suggestions have a common thread—a golden rule, if you like. Be curious.

Even in an era of open data, data science and data journalism, we still need basic statistical principles in order not to be misled by apparent patterns in the numbers.

And all of the scientific data, statistical facts and empirical evidence can't compete with the indefinable heart's desire. For if in the end, she loves you, and she chooses you…none of the rest of this will matter.

In contrast to what many people in Britain and the United States believe, the true figures on growth (as best one can judge from official national accounts data) show that Britain and the United States have not grown any more rapidly since 1980 than Germany, France, Japan, Denmark, or Sweden. In other words, the reduction of top marginal income tax rates and the rise of top incomes do not seem to have stimulated productivity (contrary to the predictions of supply-side theory) or at any rate did not stimulate productivity enough to be statistically detectable at the macro level.

ideologues of every stripe, as well as folks with interests economic, political, or personal, can interpret data and statistics to suit their own purposes...

The greatest risks are never the ones you can see and measure, but the ones you can’t see and therefore can never measure. The ones that seem so far outside the boundary of normal probability that you can’t imagine they could happen in your lifetime—even though, of course, they do happen, more often than you care to realize.

Who needs theory when you have so much information? But this is categorically the wrong attitude to take toward forecasting, especially in a field like economics where the data is so noisy.

Data scientist (noun): Person who is better at statistics than any software engineer and better at software engineering than any statistician. — Josh Wills

Descriptive statistics exist to simplify, which always implies some loss of nuance or detail.

We usually learn from debates that we seldom learn from debates.

So it is with statistics; no amount of fancy analysis can make up for fundamentally flawed data. Hence the expression “garbage in, garbage out.

Probability doesn’t make mistakes; people using probability make mistakes.

So the problem is not the algorithms, or the big datasets. The problem is a lack of scrutiny, transparency, and debate.

Not asking what a statistic actually means is a failure of empathy, too.

The newspapers kept stroking my fear. New surveys provided awful statistics on just about everything. Evidence suggested that we were not doing well. Researchers gloomily agreed. Environment psychologists were interviewed. Damage had ‘unwittingly’ been done. There were ‘feared lapses’. There were ‘misconceptions’ about potential. Situations had ‘deteriorated’. Cruelty was on the rise and there was nothing anyone could do about it. The populace was confounded, yet didn’t care. Unpublished studies hinted that we were all paying a price. Scientists peered into data and concluded that we should all be very worried. No one knew what normal behavior was anymore, and some argued that this was a form of virtue. And no one argued back. No one challenged anything. Anxiety was soaking up most people’s days. Everyone had become preoccupied with horror. Madness was fluttering everywhere. There was fifty years of research supporting this data. There were diagrams illustrating all of these problems – circles and hexagons and squares, different sections colored in lime or lilac or gray. Most troubling were the fleeting signs that nothing could transform any of this into something positive. You couldn’t help being both afraid and fascinated. Reading these articles made you feel that the survival of mankind didn’t seem very important in the long run. We were doomed. We deserved it. I was so tired.

In conclusion: when it comes to pattern recognition, we are oversensitive. Regain your scepticism. If you think you have discovered a pattern, first consider it pure chance. If it seems too good to be true, find a mathematician and have the data tested statistically. And if the crispy parts of your pancake start to look a lot like Jesus’ face, ask yourself: if he really wants to reveal himself, why doesn’t he do it in Times Square or on CNN?

The viewer of television, the listener to radio, the reader of magazines, is presented with a whole complex of elements—all the way from ingenious rhetoric to carefully selected data and statistics—to make it easy for him to “make up his own mind” with the minimum of difficulty and effort. But the packaging is often done so effectively that the viewer, listener, or reader does not make up his own mind at all. Instead, he inserts a packaged opinion into his mind, somewhat like inserting a cassette into a cassette player. He then pushes a button and “plays back” the opinion whenever it seems appropriate to do so. He has performed acceptably without having had to think.

Yet like many other human traits that made sense in past ages but cause trouble in the modern age, the knowledge illusion has its downside. The world is becoming ever more complex, and people fail to realise just how ignorant they are of what’s going on. Consequently some who know next to nothing about meteorology or biology nevertheless propose policies regarding climate change and genetically modified crops, while others hold extremely strong views about what should be done in Iraq or Ukraine without being able to locate these countries on a map. People rarely appreciate their ignorance, because they lock themselves inside an echo chamber of like-minded friends and self-confirming newsfeeds, where their beliefs are constantly reinforced and seldom challenged. Providing people with more and better information is unlikely to improve matters. Scientists hope to dispel wrong views by better science education, and pundits hope to sway public opinion on issues such as Obamacare or global warming by presenting the public with accurate facts and expert reports. Such hopes are grounded in a misunderstanding of how humans actually think. Most of our views are shaped by communal groupthink rather than individual rationality, and we hold on to these views out of group loyalty. Bombarding people with facts and exposing their individual ignorance is likely to backfire. Most people don’t like too many facts, and they certainly don’t like to feel stupid. Don’t be so sure that you can convince Tea Party supporters of the truth of global warming by presenting them with sheets of statistical data.

What makes him successful is the way that he analyzes information. He is not just hunting for patterns. Instead, Bob combines his knowledge of statistics with his knowledge of basketball in order to identify meaningful relationships in the data.

The fundamental confusion that makes income bracket data and individual income data seem mutually contradictory is the implicit assumption that people in particular income brackets at a given time are an enduring “class” at that level. If that were true, then trends over time in comparisons between income brackets would be the same as trends over time between individuals. Because that is not the case, the two sets of statistics lead not only to different conclusions but even opposite conclusions.

In addition, seculars do not sanctify any group, any person or any book as if it and it alone has sole custody of the truth. Instead, secular people sanctify the truth wherever it may reveal itself – in ancient fossilised bones, in images of far-off galaxies, in tables of statistical data, or in the writings of various human traditions. This commitment to the truth underlies modern science, which has enabled humankind to split the atom, decipher the genome, track the evolution of life, and understand the history of humanity itself

A modern fad which has gained widespread acceptance amongst the semi-educated who wish to appear secular is the practice of meditation. They proclaim with an air of smug superiority, ‘Main mandir-vandir nahin jaata, meditate karta hoon (I don’t go to temples or other such places, I meditate).’ The exercise involves sitting lotus-pose (padma asana), regulating one’s breathing and making your mind go blank to prevent it from ‘jumping about like monkeys’ from one (thought) branch to another. This intense concentration awakens the kundalini serpent coiled at the base of the spine. It travels upwards through chakras (circles) till it reaches its destination in the cranium. Then the kundalini is fully jaagrit (roused) and the person is assured to have reached his goal. What does meditation achieve? The usual answer is ‘peace of mind’. If you probe further, ‘and what does peace of mind achieve?’, you will get no answer because there is none. Peace of mind is a sterile concept which achieves nothing. The exercise may be justified as therapy for those with disturbed minds or those suffering from hypertension, but there is no evidence to prove that it enhances creativity. On the contrary it can be established by statistical data that all the great works of art, literature, science and music were works of highly agitated minds, at times minds on the verge of collapse. Allama Iqbal’s short prayer is pertinent: Khuda tujhey kisee toofaan say aashna kar dey Keh terey beher kee maujon mein iztiraab naheen (May God bring a storm in your life, There is no agitation in the waves of your life’s ocean.)

Your relevance as a data custodian is your ability to analyse and interpret it. If you can’t, your replacement is due.

A hammer looks like a useful tool to a carpenter; the nail has a different impression altogether

Van Meegeren wasn’t an artistic genius, but he intuitively understood something about human nature. Sometimes, we want to be fooled.

Signals always come with noise: It is trying to separate out the two that makes the subject interesting.

More data means that we need to be even more aware of what the evidence is actually worth.

Regression analysis is the hydrogen bomb of the statistics arsenal.

When a measure becomes a target, it ceases to be a good measure.”)

two experiments with different designs can produce identical data but different p values because the unobserved data is different. Suppose I ask you a series of 12 true-or-false questions

Far from freeing us from the need for statistical skills, bigger data and the rise in the number and complexity of scientific studies makes it even more difficult to draw appropriate conclusions.

Unlike earlier thinkers, who had sought to improve their accuracy by getting rid of error, Laplace realized that you should try to get more error: aggregate enough flawed data, and you get a glimpse of the truth. “The genius of statistics, as Laplace defined it, was that it did not ignore errors; it quantified them,” the writer Louis Menand observed. “…The right answer is, in a sense, a function of the mistakes.

That we are in the midst of crisis is now well understood. Our nation is at war, against a far-reaching network of violence and hatred. Our economy is badly weakened, a consequence of greed and irresponsibility on the part of some, but also our collective failure to make hard choices and prepare the nation for a new age. Homes have been lost; jobs shed; businesses shuttered. Our health care is too costly; our schools fail too many; and each day brings further evidence that the ways we use energy strengthen our adversaries and threaten our planet. These are the indicators of crisis, subject to data and statistics. Less measurable but no less profound is a sapping of confidence across our land — a nagging fear that America's decline is inevitable, and that the next generation must lower its sights. Today I say to you that the challenges we face are real. They are serious and they are many. They will not be met easily or in a short span of time. But know this, America — they will be met. On this day, we gather because we have chosen hope over fear, unity of purpose over conflict and discord. On this day, we come to proclaim an end to the petty grievances and false promises, the recriminations and worn out dogmas, that for far too long have strangled our politics.

what is the expression which the age demands? the age demands no expression whatever. we have seen photographs of bereaved asian mothers. we are not interested in the agony of your fumbled organs. there is nothing you can show on your face that can match the horror of this time. do not even try. you will only hold yourself up to the scorn of those who have felt things deeply. we have seen newsreels of humans in the extremities of pain and dislocation. you are playing to people who have experienced a catastrophe. this should make you very quiet. speak the words, convey the data, step aside. everyone knows you are in pain. you cannot tell the audience everything you know about love in every line of love you speak. step aside and they will know what you know because you know it already. you have nothing to teach them. you are not more beautiful than they are. you are not wiser. do not shout at them. do not force a dry entry. that is bad sex. if you show the lines of your genitals, then deliver what you promise. and remember that people do not really want an acrobat in bed. what is our need? to be close to the natural man, to be close to the natural woman. do not pretend that you are a beloved singer with a vast loyal audience which has followed the ups and downs of your life to this very moment. the bombs, flame-throwers, and all the shit have destroyed more than just the trees and villages. they have also destroyed the stage. did you think that your profession would escape the general destruction? there is no more stage. there are no more footlights. you are among the people. then be modest. speak the words, convey the data, step aside. be by yourself. be in your own room. do not put yourself on. do not act out words. never act out words. never try to leave the floor when you talk about flying. never close your eyes and jerk your head to one side when you talk about death. do not fix your burning eyes on me when you speak about love. if you want to impress me when you speak about love put your hand in your pocket or under your dress and play with yourself. if ambition and the hunger for applause have driven you to speak about love you should learn how to do it without disgracing yourself or the material. this is an interior landscape. it is inside. it is private. respect the privacy of the material. these pieces were written in silence. the courage of the play is to speak them. the discipline of the play is not to violate them. let the audience feel your love of privacy even though there is no privacy. be good whores. the poem is not a slogan. it cannot advertise you. it cannot promote your reputation for sensitivity. you are students of discipline. do not act out the words. the words die when you act them out, they wither, and we are left with nothing but your ambition. the poem is nothing but information. it is the constitution of the inner country. if you declaim it and blow it up with noble intentions then you are no better than the politicians whom you despise. you are just someone waving a flag and making the cheapest kind of appeal to a kind of emotional patriotism. think of the words as science, not as art. they are a report. you are speaking before a meeting of the explorers' club of the national geographic society. these people know all the risks of mountain climbing. they honour you by taking this for granted. if you rub their faces in it that is an insult to their hospitality. do not work the audience for gasps ans sighs. if you are worthy of gasps and sighs it will not be from your appreciation of the event but from theirs. it will be in the statistics and not the trembling of the voice or the cutting of the air with your hands. it will be in the data and the quiet organization of your presence. avoid the flourish. do not be afraid to be weak. do not be ashamed to be tired. you look good when you're tired. you look like you could go on forever. now come into my arms. you are the image of my beauty.

The realms of dating, marriage, and sex are all marketplaces, and we are the products. Some may bristle at the idea of people as products on a marketplace, but this is an incredibly prevalent dynamic. Consider the labor marketplace, where people are also the product. Just as in the labor marketplace, one party makes an offer to another, and based on the terms of this offer, the other person can choose to accept it or walk. What makes the dating market so interesting is that the products we are marketing, selling, buying, and exchanging are essentially our identities and lives. As with all marketplaces, every item in stock has a value, and that value is determined by its desirability. However, the desirability of a product isn’t a fixed thing—the desirability of umbrellas increases in areas where it is currently raining while the desirability of a specific drug may increase to a specific individual if it can cure an illness their child has, even if its wider desirability on the market has not changed. In the world of dating, the two types of desirability we care about most are: - Aggregate Desirability: What the average demand within an open marketplace would be for a relationship with a particular person. - Individual Desirability: What the desirability of a relationship with an individual is from the perspective of a specific other individual. Imagine you are at a fish market and deciding whether or not to buy a specific fish: - Aggregate desirability = The fish’s market price that day - Individual desirability = What you are willing to pay for the fish Aggregate desirability is something our society enthusiastically emphasizes, with concepts like “leagues.” Whether these are revealed through crude statements like, “that guy's an 8,” or more politically correct comments such as, “I believe she may be out of your league,” there is a tacit acknowledgment by society that every individual has an aggregate value on the public dating market, and that value can be judged at a glance. When what we have to trade on the dating market is often ourselves, that means that on average, we are going to end up in relationships with people with an aggregate value roughly equal to our own (i.e., individuals “within our league”). Statistically speaking, leagues are a real phenomenon that affects dating patterns. Using data from dating websites, the University of Michigan found that when you sort online daters by desirability, they seem to know “their place.” People on online dating sites almost never send a message to someone less desirable than them, and on average they reach out to prospects only 25% more desirable than themselves. The great thing about these markets is how often the average desirability of a person to others is wildly different than their desirability to you. This gives you the opportunity to play arbitrage with traits that other people don’t like, but you either like or don’t mind. For example, while society may prefer women who are not overweight, a specific individual within the marketplace may prefer obese women, or even more interestingly may have no preference. If a guy doesn’t care whether his partner is slim or obese, then he should specifically target obese women, as obesity lowers desirability on the open marketplace, but not from his perspective, giving him access to women who are of higher value to him than those he could secure within an open market.

The value for which P=0.05, or 1 in 20, is 1.96 or nearly 2; it is convenient to take this point as a limit in judging whether a deviation ought to be considered significant or not. Deviations exceeding twice the standard deviation are thus formally regarded as significant. Using this criterion we should be led to follow up a false indication only once in 22 trials, even if the statistics were the only guide available. Small effects will still escape notice if the data are insufficiently numerous to bring them out, but no lowering of the standard of significance would meet this difficulty.

The thing about love is that it’s irrational and stupid. I work with statistics and analyse hard data – I weigh probabilities and risks, and think in truths and facts. Truth – Ian broke my heart. Truth – Ian is the man I’ve never gotten over. Fact – Ian is a selfish player who doesn’t give a shit about me. Fact – I want to rip his clothes off and fuck his brains out.

If college admissions officers are going to encourage kids to take the same AP math class, why not statistics? Almost every career (whether in business, nonprofits, academics, law, or medicine benefits from proficiency in statistics. Being an informed, responsible citizen requires a sound knowledge of statistics, as politicians, reporters, and bloggers all rely on "data" to justify positions. [p.98]

I have stressed this distinction because it is an important one. It defines the fundamental difference between probability and statistics: the former concerns predictions based on fixed probabilities; the latter concerns the inference of those probabilities based on observed data.

Here is one of the most important things to remember when doing research that involves regression analysis: Try not to kill anyone. You can even put a little Post-it note on your computer monitor: “Do not kill people with your research.” Because some very smart people have inadvertently violated that rule.

Some readers are bound to want to take the techniques we’ve introduced here and try them on the problem of forecasting the future price of securities on the stock market (or currency exchange rates, and so on). Markets have very different statistical characteristics than natural phenomena such as weather patterns. Trying to use machine learning to beat markets, when you only have access to publicly available data, is a difficult endeavor, and you’re likely to waste your time and resources with nothing to show for it. Always remember that when it comes to markets, past performance is not a good predictor of future returns—looking in the rear-view mirror is a bad way to drive. Machine learning, on the other hand, is applicable to datasets where the past is a good predictor of the future.

The British people have been nothing but data since William I carried out the first census for the Domesday book in 1086,” he began. “All we are, and all we have ever been, are statistics, so let’s not pretend this is a catastrophic crisis that risks tearing apart the very moral fibre of our society. How do you think you are approved for credit cards and loans? How are decisions made on what you pay for insurance? How do we decide the number of immigrants allowed into our country? Acquired data. All that’s happened here is that we’ve reached a new level in our history where decisions have been made as to your importance to your country.

During the dot-com bubble, most people did not use a persuasive theory to gauge whether stock prices were too high, too low, or just right. Instead, as they watched stock prices go up, they invented explanations to rationalize what was happening. They talked about Moore’s Law, smart kids, and Alan Greenspan. Data without theory.

Most people use statistics the way a drunkard uses a lamp post, more for support than illumination.

opinion-based decision making, statistical malfeasance, and counterfeit analysis are pandemic. We are swimming in make-believe analytics.

Reducing intelligence to the statistical analysis of large data sets “can lead us,” says Levesque, “to systems with very impressive performance that are nonetheless idiot-savants.

Statistics is like a high-caliber weapon: helpful when used correctly and potentially disastrous in the wrong hands.

The algorithm seemed to be really good at distinguishing the two rather similar canines; it turned out that it was simply labeling any picture with snow as containing a wolf. An example with more serious implications was described by Janelle Shane in her book You Look Like a Thing and I Love You: an algorithm that was shown pictures of healthy skin and of skin cancer. The algorithm figured out the pattern: if there was a ruler in the photograph, it was cancer.7 If we don’t know why the algorithm is doing what it’s doing, we’re trusting our lives to a ruler detector.

The combination of Bayes and Markov Chain Monte Carlo has been called "arguably the most powerful mechanism ever created for processing data and knowledge." Almost instantaneously MCMC and Gibbs sampling changed statisticians' entire method of attacking problems. In the words of Thomas Kuhn, it was a paradigm shift. MCMC solved real problems, used computer algorithms instead of theorems, and led statisticians and scientists into a worked where "exact" meant "simulated" and repetitive computer operations replaced mathematical equations. It was a quantum leap in statistics.

No data are excluded on subjective or arbitrary grounds. No one piece of data is more highly valued than another. The consequences of this policy have to be accepted, even if they prove awkward.

Both the Environmental Protection Agency and the Department of the Interior removed from their websites the links to climate change data. The USDA removed the inspection reports of businesses accused of animal abuse by the government. The new acting head of the Consumer Financial Protection Bureau, Mick Mulvaney, said he wanted to end public access to records of consumer complaints against financial institutions. Two weeks after Hurricane Maria, statistics that detailed access to drinking water and electricity in Puerto Rico were deleted from the FEMA website. In a piece for FiveThirtyEight, Clare Malone and Jeff Asher pointed out that the first annual crime report released by the FBI under Trump was missing nearly three-quarters of the data tables from the previous year.

Thanks to Blast data, researchers now know that natural walking speed is one of the most accurate predictors of mortality that we have. The slower you walk, statistically speaking, the sooner you are likely to check out.

Monte Carlo is able to discover practical solutions to otherwise intractable problems because the most efficient search of an unmapped territory takes the form of a random walk. Today’s search engines, long descended from their ENIAC-era ancestors, still bear the imprint of their Monte Carlo origins: random search paths being accounted for, statistically, to accumulate increasingly accurate results. The genius of Monte Carlo—and its search-engine descendants—lies in the ability to extract meaningful solutions, in the face of overwhelming information, by recognizing that meaning resides less in the data at the end points and more in the intervening paths.

The viewer of television, the listener to radio, the reader of magazines, is presented with a whole complex of elements—all the way from ingenious rhetoric to carefully selected data and statistics—to make it easy for him to “make up his own mind” with the minimum of difficulty and effort. But the packaging is often done so effectively that the viewer, listener, or reader does not make up his own mind at all. Instead, he inserts a packaged opinion into his mind, somewhat like inserting a cassette into a cassette player. He then pushes a button and “plays back” the opinion whenever it seems appropriate to do so. He has performed acceptably without having had to think.

are many studies that say they can’t find a statistically significant effect of some policy change,” Hoxby says. “That doesn’t mean that there wasn’t an effect. It just means that they couldn’t find it in the data. In this study, I

Consumers of news should be aware of its built-in bias and adjust their information diet to include sources that present the bigger statistical picture: less Facebook News Feed, more Our World in Data.38 Journalists should put lurid events in context. A killing or plane crash or shark attack should be accompanied by the annual rate, which takes into account the denominator of the probability, not just the numerator. A setback or spate of misfortunes should be put into the context of the longer-term trend.

I’ve laid down ten statistical commandments in this book. First, we should learn to stop and notice our emotional reaction to a claim, rather than accepting or rejecting it because of how it makes us feel. Second, we should look for ways to combine the “bird’s eye” statistical perspective with the “worm’s eye” view from personal experience. Third, we should look at the labels on the data we’re being given, and ask if we understand what’s really being described. Fourth, we should look for comparisons and context, putting any claim into perspective. Fifth, we should look behind the statistics at where they came from—and what other data might have vanished into obscurity. Sixth, we should ask who is missing from the data we’re being shown, and whether our conclusions might differ if they were included. Seventh, we should ask tough questions about algorithms and the big datasets that drive them, recognizing that without intelligent openness they cannot be trusted. Eighth, we should pay more attention to the bedrock of official statistics—and the sometimes heroic statisticians who protect it. Ninth, we should look under the surface of any beautiful graph or chart. And tenth, we should keep an open mind, asking how we might be mistaken, and whether the facts have changed.

But psychology is passing into a less simple phase. Within a few years what one may call a microscopic psychology has arisen in Germany, carried on by experimental methods, asking of course every moment for introspective data, but eliminating their uncertainty by operating on a large scale and taking statistical means. This method taxes patience to the utmost, and could hardly have arisen in a country whose natives could be bored. Such Germans as Weber, Fechner, Vierordt, and Wundt obviously cannot ; and their success has brought into the field an array of younger experimental psychologists, bent on studying the elements of the mental life, dissecting them out from the gross results in which they are embedded, and as far as possible reducing them to quantitative scales. The simple and open method of attack having done what it can, the method of patience, starving out, and harassing to death is tried ; the Mind must submit to a regular siege, in which minute advantages gained night and day by the forces that hem her in must sum themselves up at last into her overthrow. There is little of the grand style about these new prism, pendulum, and chronograph-philosophers. They mean business, not chivalry. What generous divination, and that superiority in virtue which was thought by Cicero to give a man the best insight into nature, have failed to do, their spying and scraping, their deadly tenacity and almost diabolic cunning, will doubtless some day bring about. No general description of the methods of experimental psychology would be instructive to one unfamiliar with the instances of their application, so we will waste no words upon the attempt.

Campbell’s slideshow lists grim domestic violence statistic after statistic: second leading cause of death for African American women, third leading cause of death for native women, seventh leading cause of death for Caucasian women. Campbell says twelve hundred abused women are killed every year in the United States.1 That figure does not count children. And it does not count the abusers who kill themselves after killing their partners, murder-suicides we see daily in the newspaper. And it does not count same-sex relationships where one or the other partner might not be “out.” And it does not count other family members, like sisters, aunts, grandmothers, who are often killed alongside the primary victim. And it does not count innocent bystanders: the twenty-six churchgoers in Texas, say, after a son-in-law has gone to a service to target his mother-in-law, or the two spa employees in Wisconsin killed alongside their client by her ex. The list is endless. And it does not count the jurisdictions who do not report their homicides, since homicide reporting is voluntary through the FBI’s Supplemental Homicide Reporting Data. So how many people are killed as a result of domestic violence each year? The bystanders, the other family members, the perpetrators’ suicides? The victims who just can’t take it anymore and kill themselves? The accidents that turn out not to be accidents at all, victims pushed out of cars and from cliffs or driven into trees. Tragedies forever uncategorized.

In the name of speed, Morse and Vail had realized that they could save strokes by reserving the shorter sequences of dots and dashes for the most common letters. But which letters would be used most often? Little was known about the alphabet’s statistics. In search of data on the letters’ relative frequencies, Vail was inspired to visit the local newspaper office in Morristown, New Jersey, and look over the type cases. He found a stock of twelve thousand E’s, nine thousand T’s, and only two hundred Z’s. He and Morse rearranged the alphabet accordingly. They had originally used dash-dash-dot to represent T, the second most common letter; now they promoted T to a single dash, thus saving telegraph operators uncountable billions of key taps in the world to come. Long afterward, information theorists calculated that they had come within 15 percent of an optimal arrangement for telegraphing English text.

Avoid succumbing to the gambler’s fallacy or the base rate fallacy. Anecdotal evidence and correlations you see in data are good hypothesis generators, but correlation does not imply causation—you still need to rely on well-designed experiments to draw strong conclusions. Look for tried-and-true experimental designs, such as randomized controlled experiments or A/B testing, that show statistical significance. The normal distribution is particularly useful in experimental analysis due to the central limit theorem. Recall that in a normal distribution, about 68 percent of values fall within one standard deviation, and 95 percent within two. Any isolated experiment can result in a false positive or a false negative and can also be biased by myriad factors, most commonly selection bias, response bias, and survivorship bias. Replication increases confidence in results, so start by looking for a systematic review and/or meta-analysis when researching an area.

Baseball also has statistical rigor. Its gurus have an immense data set at hand, almost all of it directly related to the performance of players in the game. Moreover, their data is highly relevant to the outcomes they are trying to predict. This may sound obvious, but as we’ll see throughout this book, the folks building WMDs routinely lack data for the behaviors they’re most interested in. So they substitute stand-in data, or proxies. They draw statistical correlations between a person’s zip code or language patterns and her potential to pay back a loan or handle a job. These correlations are discriminatory, and some of them are illegal.

Bullshit involves language, statistical figures, data graphics, and other forms of presentation intended to persuade or impress an audience by distracting, overwhelming, or intimidating them with a blatant disregard for truth, logical coherence, or what information is actually being conveyed. The key elements of this definition are that bullshit bears no allegiance to conveying the truth, and that the bullshitter attempts to conceal this fact behind some type of rhetorical veil. Sigmund Freud illustrated the concept about as well as one could imagine in a letter he wrote his fiancée, Martha Bernays, in 1884: So I gave my lecture yesterday.

That so far the material has been dealt with in a rather subjective way provokes the question whether a means can be found of handling it objectively. [...] This chapter considers the applicability of the statistical tests employed by Wilson and the general problem whether the Linear B data are suited to statistical analysis.

Most often in culture we see people who short-circuit the Current. They observe some phenomenon in culture or nature that makes them emotional and they run rampant with speculations, never taking the time to entertain possible explanations that could have been verified by further observation. They disconnect themselves from reality and can then imagine whatever they want. On the other hand, we see many people, particularly in academia or in the sciences, who accumulate mountains of information and data from studies and statistics but never venture to speculate on the larger ramifications of this information or connect it all into a theory. They are afraid to speculate because it seems unscientific and subjective, failing to understand that speculation is the heart and soul of human rationality, our way of connecting to reality and seeing the invisible. To them, it is better to stick to facts and studies, to keep a micro view, rather than possibly embarrassing themselves with a speculation that could be wrong.

Needless to say, the anointed much prefer to quote family and household statistics on income, claiming “economic stagnation,” the “disappearance of the middle class,” and miscellaneous other rhetorical catastrophes. “For all but the top 20 percent,” an op-ed column in the New York Times said, “income has stagnated.” Moreover, this alleged fact was “widely acknowledged” by “politicians, economists and sociologists.”72 That so many such people echoed the same refrain—without bothering to check readily available census data to the contrary—says more about them than about income. Moreover, not all such use of household or family income data can be attributed to statistical naivete.

The [Value at Risk model] was like a faulty speedometer, which is arguably worse than no speedometer at all. If you place too much faith in the broken speedometer, you will be oblivious to other signs that your speed is unsafe. In contrast, if there is no speedometer at all, you have no choice but to look around for clues as to how fast you are really going.

We now have many statistical software packages. Their power is incredible, but the pioneers of statistical inference would have mixed feelings, for they always insisted that people think before using a routine. In the old days routines took endless hours to apply, so one had to spend a lot of time thinking in order to justify using a routine. Now one enters data and presses a button. One result is that people seem to be cowed into not asking silly questions, such as: What hypothesis are you testing? What distribution is it that you say is not normal? What population are you talking about? Where did this base rate come from? Most important of all: Whose judgments do you use to calibrate scores on your questionnaires? Are those judgments generally agreed to by the qualified experts in the entire community?

In the name of speed, Morse and Vail had realized that they could save strokes by reserving the shorter sequences of dots and dashes for the most common letters. But which letters would be used most often? Little was known about the alphabet’s statistics. In search of data on the letters’ relative frequencies, Vail was inspired to visit the local newspaper office in Morristown, New Jersey, and look over the type cases.

The problem is that many authors of papers in the medical literature allow statistics to become their master rather than their servant: numbers are plugged into a statistical program and the results are interpreted in a cut-and-dried fashion. Statistical significance (that two sets of data are not from the same population) is confused with clinical significance (that differences are sufficiently large to have a biological effect).

Lilah did little more than sleep and eat and cry, which to me was the most fascinating thing in the entire universe. Why did she cry? When did she sleep? What made her eat a lot one day and little the next? Was she changing with time? I did what any obsessed person would do in such a case: I recorded data, plotted it, calculated statistical correlations. First I just wrote on scraps of paper and made charts on graph paper, but I very quickly became more sophisticated. I wrote computer software to make a beautifully colored plot showing times when Diane fed Lilah, in black; when I fed her, in blue (expressed mother's milk, if you must know); Lilah's fussy times, in angry red; her happy times, in green. I calculated patterns in sleeping times, eating times, length of sleep, amounts eaten. Then, I did what any obsessed person would do these days; I put it all on the Web.

When the CERN teams reported a 'five-sigma' result for the Higgs boson, corresponding to a P-value of around 1 in 3.5 million, the BBC reported the conclusion correctly, saying this meant 'about a one-on-3.5 million chance that the signal they see would appear if there were no Higgs particle.' But nearly every other outlet got the meaning of this P-value wrong. For example, Forbes Magazine reported, 'The chances are less than 1 in a million that it is not the Higgs boson,' a clear example of the prosecutor's fallacy. The Independent was typical in claiming that 'there is less than a one in a million chance that their results are a statistical fluke.' This may not be blatantly mistaken as Forbes, but it is still assigning the small probability to 'their results are a statistical fluke', which is logically the same as saying this is the probability of the null hypothesis being tested.

As it happens, there’s a way of presenting data, called the funnel plot, that indicates whether or not the scientific literature is biased in this way.15 (If statistics don’t excite you, feel free to skip straight to the probably unsurprising conclusion in the last sentence of this paragraph.) You plot the data points from all your studies according to the effect sizes, running along the horizontal axis, and the sample size (roughly)16 running up the vertical axis. Why do this? The results from very large studies, being more “precise,” should tend to cluster close to the “true” size of the effect. Smaller studies by contrast, being subject to more random error because of their small, idiosyncratic samples, will be scattered over a wider range of effect sizes. Some small studies will greatly overestimate a difference; others will greatly underestimate it (or even “flip” it in the wrong direction). The next part is simple but brilliant. If there isn’t publication bias toward reports of greater male risk taking, these over- and underestimates of the sex difference should be symmetrical around the “true” value indicated by the very large studies. This, with quite a bit of imagination, will make the plot of the data look like an upside-down funnel. (Personally, my vote would have been to call it the candlestick plot, but I wasn’t consulted.) But if there is bias, then there will be an empty area in the plot where the smaller samples that underestimated the difference, found no differences, or yielded greater female risk taking should be. In other words, the overestimates of male risk taking get published, but various kinds of “underestimates” do not. When Nelson plotted the data she’d been examining, this is exactly what she found: “Confirmation bias is strongly indicated.”17 This

Our brain is therefore not simply passively subjected to sensory inputs. From the get-go, it already possesses a set of abstract hypotheses, an accumulated wisdom that emerged through the sift of Darwinian evolution and which it now projects onto the outside world. Not all scientists agree with this idea, but I consider it a central point: the naive empiricist philosophy underlying many of today's artificial neural networks is wrong. It is simply not true that we are born with completely disorganized circuits devoid of any knowledge, which later receive the imprint of their environment. Learning, in man and machine, always starts from a set of a priori hypotheses, which are projected onto the incoming data, and from which the system selects those that are best suited to the current environment. As Jean-Pierre Changeux stated in his best-selling book Neuronal Man (1985), “To learn is to eliminate.

The master propagandist, like the advertising expert, avoids obvious emotional appeals and strives for a tone that is consistent with the prosaic quality of modern life—a dry, bland matter-of-factness. Nor does the propagandist circulate "intentionally biased" information. He knows that partial truths serve as more effective instruments of deception than lies. Thus he tries to impress the public with statistics of economic growth that neglect to give the base year from which growth is calculated, with accurate but meaningless facts about the standard of living—with raw and uninterpreted data, in other words, from which the audience is invited to draw the inescapable conclusion that things are getting better and the present régime therefore deserves the people's confidence, or on the other hand that things are getting worse so rapidly that the present régime should be given emergency powers to deal with the developing crisis.

In trying to comprehend and judge moral dilemmas of this scale, people often resort to one of four methods. The first is to downsize the issue. To understand the Syrian civil war as though it were occurring between two foragers, for example, one imagines the Assad regime as a lone person and the rebels as another person; one of them is bad and one of them is good. The historical complexity of the conflict is replaced by a simple, clear plot.4 The second method is to focus on a touching human story that ostensibly stands for the whole conflict. When you try to explain to people the true complexity of the conflict by means of statistics and precise data, you lose them, but a personal story about the fate of one child activates the tear ducts, makes the blood boil, and generates false moral certainty.5 This is something that many charities have understood for a long time. In one noteworthy experiment, people were asked to donate money to help a poor seven-year-old girl from Mali named Rokia. Many were moved by her story and opened their hearts and purses. However, when in addition to Rokia’s personal story the researchers also presented people with statistics about the broader problem of poverty in Africa, respondents suddenly became less willing to help. In another study, scholars solicited donations to help either one sick child or eight sick children. People gave more money to the single child than to the group of eight.6

If we had enough data then this statistical approach would undoubtedly sort out these things, and a lot of problems are arising precisely because we haven't got enough documents for the statistical approach to be wholly valid. I know you can calculate levels of probability and so forth, but to establish this really clearly we want a lot more information than we have actually got available. This is surely our major problem that we are still at the very limits at which you can use a technique of this sort. - John Chadwick

(…) it may be seriously questioned whether the advent of modern communications media has much enhanced our understanding of the world in which we live.(…) Perhaps we know more about the world than we used to, and insofar as knowledge is prerequisite to understanding, that is all to the good. But knowledge is not as much a prerequisite to understanding as is commonly supposed. We do not have to know everything about something in order to understand it; too many facts are often as much of an obstacle to understanding as too few. There is a sense in which we moderns are inundated with facts to the detriment of understanding. (…) One of the reasons for this situation is that the very media we have mentioned are so designed as to make thinking seem unnecessary (though this is only an appearance). The packaging of intellectual positions and views is one of the most active enterprises of some of the best minds of our day. The viewer of television, the listener to radio, the reader of magazines, is presented with a whole complex of elements—all the way from ingenious rhetoric to carefully selected data and statistics—to make it easy for him to “make up his own mind” with the minimum of difficulty and effort. But the packaging is often done so effectively that the viewer, listener, or reader does not make up his own mind at all. Instead, he inserts a packaged opinion into his mind, somewhat like inserting a cassette into a cassette player. He then pushes a button and “plays back” the opinion whenever it seems appropriate to do so. He has performer acceptably without having had to think.

Goethe (I don’t know why, but Goethe somehow always speaks up in my critical moments) said: “Man must experience his own destiny” - not a factual destiny forced on him by History, but the nonrecurrent, his very own. Perhaps this was possible a hundred years ago. At the time of the French Revolution and also of the Napoleonic Wars, an individual still had the means of turning against the collective destiny adroitly, cunningly. He could hide or build emergency dams hastily in his soul. And a hundred years ago when someone mounted the scaffold or fell on the battlefield, he knew that what was then being consummated personally was his destiny. But today? There is no longer a “personal destiny;” there are only statistical probabilities. One cannot feel it to be personal destiny when an atom bomb explodes or when a dictatorship enunciates an outmoded, stupid judgment on a society. This is why I must go somewhere from this place where, perhaps, it will be possible for me to live my own destiny for a time. Because here I have already become only a piece of data in a category.

Listen, Google,’ I will say, ‘both John and Paul are courting me. I like both of them, but in a different way, and it’s so hard to make up my mind. Given everything you know, what do you advise me to do?’ And Google will answer: ‘Well, I know you from the day you were born. I have read all your emails, recorded all your phone calls, and know your favourite films, your DNA and the entire history of your heart. I have exact data about each date you went on, and if you want, I can show you second-by-second graphs of your heart rate, blood pressure and sugar levels whenever you went on a date with John or Paul. If necessary, I can even provide you with accurate mathematical ranking of every sexual encounter you had with either of them. And naturally enough, I know them as well as I know you. Based on all this information, on my superb algorithms, and on decades’ worth of statistics about millions of relationships – I advise you to go with John, with an 87 per cent probability of being more satisfied with him in the long run. Indeed, I know you so well that I also know you don’t like this answer. Paul is much more handsome than John, and because you give external appearances too much weight, you secretly wanted me to say “Paul”. Looks matter, of course; but not as much as you think. Your biochemical algorithms – which evolved tens of thousands of years ago in the African savannah – give looks a weight of 35 per cent in their overall rating of potential mates. My algorithms – which are based on the most up-to-date studies and statistics – say that looks have only a 14 per cent impact on the long-term success of romantic relationships. So, even though I took Paul’s looks into account, I still tell you that you would be better off with John.

If there were a strong correlation between Christian conservatism and societal health, we might expect to see some sign of it in red-state America. We don’t. Of the twenty-five cities with the lowest rates of violent crime, 62 percent are in “blue” states and 38 percent are in “red” states. Of the twenty-five most dangerous cities, 76 percent are in red states, 24 percent in blue states. In fact, three of the five most dangerous cities in the United States are in the pious state of Texas. The twelve states with the highest rates of burglary are red. Twenty-four of the twenty-nine states with the highest rates of theft are red. Of the twenty-two states with the highest rates of murder, seventeen are red. Of course, correlational data of this sort do not resolve questions of causality—belief in God may lead to societal dysfunction; societal dysfunction may foster a belief in God; each factor may enable the other; or both may spring from some deeper source of mischief. Leaving aside the issue of cause and effect, however, these statistics prove that atheism is compatible with the basic aspirations of a civil society; they also prove, conclusively, that widespread belief in God does not ensure a society’s health.

1:THE “CRISIS”: Although Chief Judge Bazelon said in 1960 that “we desperately need all the help we can get from modern behavioral scientists”69 in dealing with the criminal law, the cold facts suggest no such desperation or crisis. Since the most reliable long-term crime data are on murder, what was the murder rate at that point? The number of murders committed in the United States in 1960 was less than in 1950, 1940, or 1930—even though the population was growing over those decades and murders in the two new states of Hawaii and Alaska were counted in the national statistics for the first time in 1960.70 The murder rate, in proportion to population, was in 1960 just under half of what it had been in 1934.71 As Judge Bazelon saw the criminal justice system in 1960, the problem was not with “the so-called criminal population”72 but with society, whose “need to punish” was a “primitive urge” that was “highly irrational”73—indeed, a “deep childish fear that with any reduction of punishment, multitudes would run amuck.”74 It was this “vindictiveness,” this “irrationality” of “notions and practices regarding punishment”75 that had to be corrected. The criminal “is like us, only somewhat weaker,” according to Judge Bazelon, and “needs help if he is going to bring out the good in himself and restrain the bad.”76 Society is indeed guilty of “creating this special class of human beings,” by its “social failure” for which “the criminal serves as a scapegoat.”77 Punishment is itself a “dehumanizing process” and a “social branding” which only promotes more crime.78 Since criminals “have a special problem and need special help,” Judge Bazelon argued for “psychiatric treatment” with “new, more sophisticated techniques” and asked: Would it really be the end of the world if all jails were turned into hospitals or rehabilitation centers?79

What are the health effects of the choice between austerity and stimulus? Today there is a vast natural experiment being conducted on the body economic. It is similar to the policy experiments that occurred in the Great Depression, the post-communist crisis in eastern Europe, and the East Asian Financial Crisis. As in those prior trials, health statistics from the Great Recession reveal the deadly price of austerity—a price that can be calculated not just in the ticks to economic growth rates, but in the number of years of life lost and avoidable deaths. Had the austerity experiments been governed by the same rigorous standards as clinical trials, they would have been discontinued long ago by a board of medical ethics. The side effects of the austerity treatment have been severe and often deadly. The benefits of the treatment have failed to materialize. Instead of austerity, we should enact evidence-based policies to protect health during hard times. Social protection saves lives. If administered correctly, these programs don’t bust the budget, but—as we have shown throughout this book—they boost economic growth and improve public health. Austerity’s advocates have ignored evidence of the health and economic consequences of their recommendations. They ignore it even though—as with the International Monetary Fund—the evidence often comes from their own data. Austerity’s proponents, such as British Prime Minister David Cameron, continue to write prescriptions of austerity for the body economic, in spite of evidence that it has failed. Ultimately austerity has failed because it is unsupported by sound logic or data. It is an economic ideology. It stems from the belief that small government and free markets are always better than state intervention. It is a socially constructed myth—a convenient belief among politicians taken advantage of by those who have a vested interest in shrinking the role of the state, in privatizing social welfare systems for personal gain. It does great harm—punishing the most vulnerable, rather than those who caused this recession.

It has often been claimed that there has been very little change in the average real income of American households over a period of decades. It is an undisputed fact that the average real income—that is, money income adjusted for inflation—of American households rose by only 6 percent over the entire period from 1969 to 1996. That might well be considered to qualify as stagnation. But it is an equally undisputed fact that the average real income per person in the United States rose by 51 percent over that very same period.3 How can both these statistics be true? Because the average number of individuals per household has been declining over the years. Half the households in the United States contained six or more people in 1900, as did 21 percent in 1950. But, by 1998, only ten percent of American households had that many people.4 The average number of persons per household not only varies over time, it also varies from one racial or ethnic group to another at a given time, and varies from one income bracket to another. As of 2007, for example, black household income was lower than Hispanic household income, even though black per capita income was higher than Hispanic per capita income, because black households average fewer people than Hispanic households. Similarly, Asian American household income was higher than white household income, even though white per capita income was higher than Asian American per capita income, because Asian American households average more people.5 Income comparisons using household statistics are far less reliable indicators of standards of living than are individual income data because households vary in size while an individual always means one person. Studies of what people actually consume—that is, their standard of living—show substantial increases over the years, even among the poor,6 which is more in keeping with a 51 percent increase in real per capita income than with a 6 percent increase in real household income. But household income statistics present golden opportunities for fallacies to flourish, and those opportunities have been seized by many in the media, in politics, and in academia.

In the EPJ results, there were two statistically distinguishable groups of experts. The first failed to do better than random guessing, and in their longer-range forecasts even managed to lose to the chimp. The second group beat the chimp, though not by a wide margin, and they still had plenty of reason to be humble. Indeed, they only barely beat simple algorithms like “always predict no change” or “predict the recent rate of change.” Still, however modest their foresight was, they had some. So why did one group do better than the other? It wasn’t whether they had PhDs or access to classified information. Nor was it what they thought—whether they were liberals or conservatives, optimists or pessimists. The critical factor was how they thought. One group tended to organize their thinking around Big Ideas, although they didn’t agree on which Big Ideas were true or false. Some were environmental doomsters (“We’re running out of everything”); others were cornucopian boomsters (“We can find cost-effective substitutes for everything”). Some were socialists (who favored state control of the commanding heights of the economy); others were free-market fundamentalists (who wanted to minimize regulation). As ideologically diverse as they were, they were united by the fact that their thinking was so ideological. They sought to squeeze complex problems into the preferred cause-effect templates and treated what did not fit as irrelevant distractions. Allergic to wishy-washy answers, they kept pushing their analyses to the limit (and then some), using terms like “furthermore” and “moreover” while piling up reasons why they were right and others wrong. As a result, they were unusually confident and likelier to declare things “impossible” or “certain.” Committed to their conclusions, they were reluctant to change their minds even when their predictions clearly failed. They would tell us, “Just wait.” The other group consisted of more pragmatic experts who drew on many analytical tools, with the choice of tool hinging on the particular problem they faced. These experts gathered as much information from as many sources as they could. When thinking, they often shifted mental gears, sprinkling their speech with transition markers such as “however,” “but,” “although,” and “on the other hand.” They talked about possibilities and probabilities, not certainties. And while no one likes to say “I was wrong,” these experts more readily admitted it and changed their minds. Decades ago, the philosopher Isaiah Berlin wrote a much-acclaimed but rarely read essay that compared the styles of thinking of great authors through the ages. To organize his observations, he drew on a scrap of 2,500-year-old Greek poetry attributed to the warrior-poet Archilochus: “The fox knows many things but the hedgehog knows one big thing.” No one will ever know whether Archilochus was on the side of the fox or the hedgehog but Berlin favored foxes. I felt no need to take sides. I just liked the metaphor because it captured something deep in my data. I dubbed the Big Idea experts “hedgehogs” and the more eclectic experts “foxes.” Foxes beat hedgehogs. And the foxes didn’t just win by acting like chickens, playing it safe with 60% and 70% forecasts where hedgehogs boldly went with 90% and 100%. Foxes beat hedgehogs on both calibration and resolution. Foxes had real foresight. Hedgehogs didn’t.