What do you think?
Rate this book
Numbers Rule Your World: The Hidden Influence of Probabilities and Statistics on Everything You Do
WHAT ARE THE ODDS YOU'LL WIN THE LOTTERY?
How long will your kids wait in line at Disney World? Who decides that “standardized tests� are fair? Why do highway engineers build slow-moving ramps? What does it mean, statistically, to be an “Average Joe�? NUMBERS RULE YOUR WORLD
In the popular tradition of eye-opening bestsellers like Freakonomics, The Tipping Point, and Super Crunchers, this fascinating book from renowned statistician and blogger Kaiser Fung takes you inside the hidden world of facts and figures that affect you every day, in every way. These are the statistics that rule your life, your job, your commute, your vacation, your food, your health, your money, and your success. This is how engineers calculate your quality of living, how corporations determine your needs, and how politicians estimate your opinions. These are the numbers you never think about-even though they play a crucial role in every single aspect of your life. What you learn may surprise you, amuse you, or even enrage you. But there's one thing you won't be able to deny: Numbers Rule Your World� "An easy read with a big benefit."
―Fareed Zakaria, CNN "For those who have anxiety about how organization data-mining is impacting their world, Kaiser Fung pulls back the curtain to reveal the good and the bad of predictive analytics."
―Ian Ayres,Yale professor and author of Super Crunchers: Why Thinking By Numbers is the New Way to Be Smart
"A book that engages us with stories that a journalist would write, the compelling stories behind the stories as illuminated by the numbers, and the dynamics that the numbers reveal."
―John Sall, Executive Vice President, SAS Institute "Little did I suspect, when I picked up Kaiser Fung's book, that I would become so entranced by it - an illuminating and accessible exploration of the power of statistical analysis for those of us who have no prior training in a field that he explores so ably."
―Peter Clarke, author of Keynes: The Rise, Fall, and Return of the 20th Century's Most Influential Economist "A tremendous book. . . . If you want to understand how to use statistics, how to think with numbers and yet to do this without getting lost in equations, if you've been looking for the book to unlock the door to logical thinking about problems, well, you will be pleased to know that you are holding that book in your hands."
―Daniel Finkelstein, Executive Editor, The Times of London "I thoroughly enjoyed this accessible book and enthusiastically recommend it to anyone looking to understand and appreciate the role of statistics and data analysis in solving problems and in creating a better world."
―Michael Sherman, Texas A&M University, American Statistician
How long will your kids wait in line at Disney World? Who decides that “standardized tests� are fair? Why do highway engineers build slow-moving ramps? What does it mean, statistically, to be an “Average Joe�? NUMBERS RULE YOUR WORLD
In the popular tradition of eye-opening bestsellers like Freakonomics, The Tipping Point, and Super Crunchers, this fascinating book from renowned statistician and blogger Kaiser Fung takes you inside the hidden world of facts and figures that affect you every day, in every way. These are the statistics that rule your life, your job, your commute, your vacation, your food, your health, your money, and your success. This is how engineers calculate your quality of living, how corporations determine your needs, and how politicians estimate your opinions. These are the numbers you never think about-even though they play a crucial role in every single aspect of your life. What you learn may surprise you, amuse you, or even enrage you. But there's one thing you won't be able to deny: Numbers Rule Your World� "An easy read with a big benefit."
―Fareed Zakaria, CNN "For those who have anxiety about how organization data-mining is impacting their world, Kaiser Fung pulls back the curtain to reveal the good and the bad of predictive analytics."
―Ian Ayres,Yale professor and author of Super Crunchers: Why Thinking By Numbers is the New Way to Be Smart
"A book that engages us with stories that a journalist would write, the compelling stories behind the stories as illuminated by the numbers, and the dynamics that the numbers reveal."
―John Sall, Executive Vice President, SAS Institute "Little did I suspect, when I picked up Kaiser Fung's book, that I would become so entranced by it - an illuminating and accessible exploration of the power of statistical analysis for those of us who have no prior training in a field that he explores so ably."
―Peter Clarke, author of Keynes: The Rise, Fall, and Return of the 20th Century's Most Influential Economist "A tremendous book. . . . If you want to understand how to use statistics, how to think with numbers and yet to do this without getting lost in equations, if you've been looking for the book to unlock the door to logical thinking about problems, well, you will be pleased to know that you are holding that book in your hands."
―Daniel Finkelstein, Executive Editor, The Times of London "I thoroughly enjoyed this accessible book and enthusiastically recommend it to anyone looking to understand and appreciate the role of statistics and data analysis in solving problems and in creating a better world."
―Michael Sherman, Texas A&M University, American Statistician
208 pages, Hardcover
First published January 25, 2010
89 people are currently reading
3,393 people want to read
Ratings & Reviews
Friends & Following
Create a free account to discover what your friends think of this book!
Community Reviews
Displaying 1 - 30 of 80 reviews
May 15, 2020
Q:
The crown jewel in Disney’s operating manual is perception management.
A body of scholarly research supports the view that crowd control is much more than a mathematical problem or an engineering puzzle; it has a human, psychological, touchy-feely dimension. A key tenet of this research—that perceived waiting time does not equal actual waiting time—has been demonstrated in multiple studies. Mirrors in elevator lobbies, for example, distort people’s sense of the amount of waiting time; we tend not to count time spent looking at our reflection as waiting time. Accordingly, Disney engineers, or “Imagineers,� devote a lot of effort to shaping patrons� perception of waiting times. By contrast, engineering solutions, including ramp metering, tend to target reductions in actual waiting times; these efforts may fail because people misjudge how much time they have stood in lines or stalled their cars. (c)
Q:
the power of this classic strategy of underpromising and overdelivering. (c)
Q:
The crown jewel in Disney’s operating manual is perception management.
A body of scholarly research supports the view that crowd control is much more than a mathematical problem or an engineering puzzle; it has a human, psychological, touchy-feely dimension. A key tenet of this research—that perceived waiting time does not equal actual waiting time—has been demonstrated in multiple studies. Mirrors in elevator lobbies, for example, distort people’s sense of the amount of waiting time; we tend not to count time spent looking at our reflection as waiting time. Accordingly, Disney engineers, or “Imagineers,� devote a lot of effort to shaping patrons� perception of waiting times. By contrast, engineering solutions, including ramp metering, tend to target reductions in actual waiting times; these efforts may fail because people misjudge how much time they have stood in lines or stalled their cars. (c)
Q:
the power of this classic strategy of underpromising and overdelivering. (c)
Q:
July 7, 2022
“The probability of dying in a plane crash is about 1:10,000,000�. That means, one passenger would die in every 10 million passengers who travel by flights.
That’s an interesting statistics to be more practical and think of the vast positive side of flight journey in which thousands of passengers land safely at their desired destinations every day. Well, you don’t need to be an expert to assess the probability of plane crashes and deaths around the world because it’s an open information. But what if you got some ingeniously manipulated numbers (statistics), and you have to make critical decisions based on that numbers !!!
The book talks about how people are misled by numbers every day � from buying things to making investment decisions or even supporting a political party and its policies based on false numbers/statistics. The author uncovers some interesting facts about statistics - how is it prepared, what techniques used, and how is it manipulated to attract the target crowd and so on.
The book clarifies the logical reasoning behind statistical patterns along with many benefits of statistics. It also describes the limitations of statistics that lead to entirely wrong decisions like on some occasions, statistics didn’t accurately detect the real criminals, or athletes who used drugs. This is because the statistics too has its inherent inability or limitations.
The author stresses five important things to reflect when making decisions based on statistics;
1. You need to remember not all the averages are the same in statistics
2. Correlation does not imply causation
3. Group differences exist in statistics
4. Sometimes data trade-off is inevitable for conclusions
5. Always question the patterns - whether they appear obvious or odd
The book is boring at some places. Yet, it could be a useful read for anyone who seeks to enhance decision accuracy.
That’s an interesting statistics to be more practical and think of the vast positive side of flight journey in which thousands of passengers land safely at their desired destinations every day. Well, you don’t need to be an expert to assess the probability of plane crashes and deaths around the world because it’s an open information. But what if you got some ingeniously manipulated numbers (statistics), and you have to make critical decisions based on that numbers !!!
The book talks about how people are misled by numbers every day � from buying things to making investment decisions or even supporting a political party and its policies based on false numbers/statistics. The author uncovers some interesting facts about statistics - how is it prepared, what techniques used, and how is it manipulated to attract the target crowd and so on.
The book clarifies the logical reasoning behind statistical patterns along with many benefits of statistics. It also describes the limitations of statistics that lead to entirely wrong decisions like on some occasions, statistics didn’t accurately detect the real criminals, or athletes who used drugs. This is because the statistics too has its inherent inability or limitations.
The author stresses five important things to reflect when making decisions based on statistics;
1. You need to remember not all the averages are the same in statistics
2. Correlation does not imply causation
3. Group differences exist in statistics
4. Sometimes data trade-off is inevitable for conclusions
5. Always question the patterns - whether they appear obvious or odd
The book is boring at some places. Yet, it could be a useful read for anyone who seeks to enhance decision accuracy.
April 19, 2010
I have to say that I thought this "pop statistics" book was much better than others I have previously read (Super Crunchers and the Freakonomics series). (Disclaimer: I have read Kaiser Fung's blog Junk Charts for a few years, so I was predisposed to think positively of his book.)
I found this book to be less into the sensational aspects of using data to make decisions and more about the challenges of doing so. Also, it explored the fact that context makes a difference. Each chapter was set up to have two examples of data analysis based on a theme of statistics, but the context of the two problems would dictate different approaches to each problem. For example, one chapter deals with the "correlation does not imply causation" them of statistics. Fung gives two examples: credit scoring and food recalls. In the credit scoring situation, the analysts do not even care about the causes of good or bad creditworthiness as long as their models are accurately predicting the risk of default on a loan. Conversely, epidemiologists involved in food recalls must worry about causation so they know precisely which food to recall. For this, Fung also discusses ways that statisticians work with other professionals to solve a problem.
All in all, I enjoyed this book and the structure of the chapters. The tone was less sensational than others, and I think that made it easier to read and take seriously. Also, I really liked that Fung did not create any new proper nouns (like "Super Cruncher").
I found this book to be less into the sensational aspects of using data to make decisions and more about the challenges of doing so. Also, it explored the fact that context makes a difference. Each chapter was set up to have two examples of data analysis based on a theme of statistics, but the context of the two problems would dictate different approaches to each problem. For example, one chapter deals with the "correlation does not imply causation" them of statistics. Fung gives two examples: credit scoring and food recalls. In the credit scoring situation, the analysts do not even care about the causes of good or bad creditworthiness as long as their models are accurately predicting the risk of default on a loan. Conversely, epidemiologists involved in food recalls must worry about causation so they know precisely which food to recall. For this, Fung also discusses ways that statisticians work with other professionals to solve a problem.
All in all, I enjoyed this book and the structure of the chapters. The tone was less sensational than others, and I think that made it easier to read and take seriously. Also, I really liked that Fung did not create any new proper nouns (like "Super Cruncher").
December 11, 2009
You don't need to be a "numbers person" (read: geek) to enjoy the fantasic and mind-boggling things some really smart people do with them. Fung manages to make the book an entertaining and speedy read while still boggling your mind with the secret statistics behind life's regular events.
And more importantly, this book could finally put the lottery debate to bed once and for all. Meaning, yes - it is silly to waste money on lotto tickets because the chances of winning or so, so slim.
And more importantly, this book could finally put the lottery debate to bed once and for all. Meaning, yes - it is silly to waste money on lotto tickets because the chances of winning or so, so slim.
October 29, 2011
Slightly deeper reading on the probabilities and statistics that affect you everyday. Author Kaiser Fung writes how you are directly changed by numbers day-by-day rather than just generating another book about the theoretical probability of something happening.
Chapter 1:
Looks at two examples of waiting time: Minnesota's road system and Disneyland's ride lines. How can the time of waiting be reduced? Author Fung proves that increasing road width and park size will do nothing. The solution lies in reducing variability and increasing reliability for drivers and guests.
We like to look at the average. But looking at the average proves that we rely on variability. It could take 30 minutes to get to work or only 7 minutes, depending on different factors. So satisfaction for us goes down. We're either too early or too late...
Disney & MN/DOT brainstormed out successful ways by reducing variability: the FastPass & "ramp metering." Ingenious creations for saving time. But then brings the argument of social injustice. "How come I have to sit here at the stop light? How come they get to cut in line?" It's all about perception! Everyone is saving time, but it doesn't feel like it on the surface.
Chapter 2:
Slightly boring chapter about a "particular breed of statisticians call modelers....Their special talent is the educated guess." The chapter compares two groups: epidemiologists & credit modelers. Epidemiologists seek to find the cause of disease outbreaks. Credit modelers determine your credit score. But how do they figure where the disease came from and how to stop it? And what variables determined my credit score (how did that guy get a higher score than me)? Modelers look at correlations to find causation. Sure, some correlations might be theoretical and wrong; but through trial and error, we can arrive at the cause.
Chapter 3:
This chapter reveals the dilemma of being lumped together in a group (focusing on test-taking analytics and the risks of Florida's home insurance). Insurance benefits high risk contributors but does little for those who live, for example, in the middle of Florida rather than the coastline. Take for instance, hurricane season...rates skyrocket. But how does that benefit the inland Floridians? Sometimes being lumped into the group doesn't help everyone.
The author compares test-taking results as well. What is fair for all demographics? Do some questions benefit one group over the other? Does lumping the group together benefit everyone? It actually doesn't. Caucasians grew up in a different environment than African Americans, and the same goes for Hispanic students. How can we create a test that is neutral to all cultures? Analysts were able to formulate SAT questions to do just this.
Author Fung wonders when this same type of equality will reach the insurance world as well.
Chapter 4:
A huge problem sits within the world of lie detection. In man's effort to seek out the "bad eggs," lie detectors falsely accuse the innocent at the same time. Fung writes about the increasing number of false positives that ruin the effectiveness of lie detection. Take drug-testing in sports...administrators blanket drug tests over all players to weed out the cheaters. From this drug-testing results many false negatives, which in turn truly end up to be false. But through the process, players reputations and careers are jeopardized. What opportunities were lost because one of these false positives came up against them? And on top of all this, the majority of drug users aren't ever caught! So is this the best method?
Fung also looks at lie detection. Instead of screening people (which could create a countless number of false negatives) with a polygraph machine, Fung argues that a police lineup would be more effective...
In the end, Fung reveals that polygraphs and data-mining detections can't help find the true wrongdoers effectively. The process produces too many false negatives. Too many people are falsely accused in an effort to find the one "bad egg." Fung offers no suggestions for improvement though, so I guess we are just left to wonder.
Chapter 5:
Great chapter revealing the honest truth behind winning the lottery and plane crashes. Both oddities rarely occur. But yet, millions of people chance their money away at the lottery ticket. Literally, the odds to win are 1 in 10 million (specifically for the Encore lottery). That statistic matches the same stat for someone to die in a plane crash. Both are freak happenings. "Yet about 50 percent of Americans play the state lotteries, and at least 30 percent fear flying." Why? It boils down to our emotions. The payoff for winning the lottery is so great! We'd love to be a part of that. But on the flip side, we could die! We don't want that...so we choose not to fly. When in reality, both occurrences will probably never affect us in this life. They would happen once every 24,000 years for us.
Numbers surround us everyday. Statistics can't predict and explain some of the mysteries of the world.
Chapter 1:
Looks at two examples of waiting time: Minnesota's road system and Disneyland's ride lines. How can the time of waiting be reduced? Author Fung proves that increasing road width and park size will do nothing. The solution lies in reducing variability and increasing reliability for drivers and guests.
We like to look at the average. But looking at the average proves that we rely on variability. It could take 30 minutes to get to work or only 7 minutes, depending on different factors. So satisfaction for us goes down. We're either too early or too late...
Disney & MN/DOT brainstormed out successful ways by reducing variability: the FastPass & "ramp metering." Ingenious creations for saving time. But then brings the argument of social injustice. "How come I have to sit here at the stop light? How come they get to cut in line?" It's all about perception! Everyone is saving time, but it doesn't feel like it on the surface.
Chapter 2:
Slightly boring chapter about a "particular breed of statisticians call modelers....Their special talent is the educated guess." The chapter compares two groups: epidemiologists & credit modelers. Epidemiologists seek to find the cause of disease outbreaks. Credit modelers determine your credit score. But how do they figure where the disease came from and how to stop it? And what variables determined my credit score (how did that guy get a higher score than me)? Modelers look at correlations to find causation. Sure, some correlations might be theoretical and wrong; but through trial and error, we can arrive at the cause.
Chapter 3:
This chapter reveals the dilemma of being lumped together in a group (focusing on test-taking analytics and the risks of Florida's home insurance). Insurance benefits high risk contributors but does little for those who live, for example, in the middle of Florida rather than the coastline. Take for instance, hurricane season...rates skyrocket. But how does that benefit the inland Floridians? Sometimes being lumped into the group doesn't help everyone.
The author compares test-taking results as well. What is fair for all demographics? Do some questions benefit one group over the other? Does lumping the group together benefit everyone? It actually doesn't. Caucasians grew up in a different environment than African Americans, and the same goes for Hispanic students. How can we create a test that is neutral to all cultures? Analysts were able to formulate SAT questions to do just this.
Author Fung wonders when this same type of equality will reach the insurance world as well.
Chapter 4:
A huge problem sits within the world of lie detection. In man's effort to seek out the "bad eggs," lie detectors falsely accuse the innocent at the same time. Fung writes about the increasing number of false positives that ruin the effectiveness of lie detection. Take drug-testing in sports...administrators blanket drug tests over all players to weed out the cheaters. From this drug-testing results many false negatives, which in turn truly end up to be false. But through the process, players reputations and careers are jeopardized. What opportunities were lost because one of these false positives came up against them? And on top of all this, the majority of drug users aren't ever caught! So is this the best method?
Fung also looks at lie detection. Instead of screening people (which could create a countless number of false negatives) with a polygraph machine, Fung argues that a police lineup would be more effective...
In the end, Fung reveals that polygraphs and data-mining detections can't help find the true wrongdoers effectively. The process produces too many false negatives. Too many people are falsely accused in an effort to find the one "bad egg." Fung offers no suggestions for improvement though, so I guess we are just left to wonder.
Chapter 5:
Great chapter revealing the honest truth behind winning the lottery and plane crashes. Both oddities rarely occur. But yet, millions of people chance their money away at the lottery ticket. Literally, the odds to win are 1 in 10 million (specifically for the Encore lottery). That statistic matches the same stat for someone to die in a plane crash. Both are freak happenings. "Yet about 50 percent of Americans play the state lotteries, and at least 30 percent fear flying." Why? It boils down to our emotions. The payoff for winning the lottery is so great! We'd love to be a part of that. But on the flip side, we could die! We don't want that...so we choose not to fly. When in reality, both occurrences will probably never affect us in this life. They would happen once every 24,000 years for us.
Numbers surround us everyday. Statistics can't predict and explain some of the mysteries of the world.
December 18, 2011
A fine little discussion of the impact of statistics on our everyday lives, in the tradition of Freakonomics. If I were asked to pick an alternative and more cynical title for this, it might be 'The Foolishness of Crowds' as Kaiser Fung offers a number of excellent examples of public perception being at odds with the reality revealed by statistics. Give people the feeling of being in control and they tend to see everything through rose-tinted glasses even though they may actually be better off surrendering that control to expert hands. An example of this is the impact of ramp metering on U.S. highways, which is unpopular even though it is provably successful in reducing journey times and congestion.
But institutions also ignore or misinterpret statistics at their peril, and this can lead to great harm. For instance, failure to understand the statistical balance that exists between false positive and false negative results in forensic procedures such as lie detection and drugs testing can lead to miscarriages of justice (and has done so).
All in all, a worthwhile read for anyone who wants to move beyond the over-simplified aphorism of 'There are lies, damned lies and statistics'.
But institutions also ignore or misinterpret statistics at their peril, and this can lead to great harm. For instance, failure to understand the statistical balance that exists between false positive and false negative results in forensic procedures such as lie detection and drugs testing can lead to miscarriages of justice (and has done so).
All in all, a worthwhile read for anyone who wants to move beyond the over-simplified aphorism of 'There are lies, damned lies and statistics'.
August 26, 2020
Numbers play an imperative role in our lives. Almost all the things we do engage numbers and Mathematics. Whether we like it or not, our life revolves in numbers since the day we were born. There are abundant numbers unswervingly or circuitously connected to our lives. From calling a member of a family or a friend using mobile phone to looking for the number of people who liked your post on Facebook and computing the interest you gained on your business, numbers are everywhere.
The ten stories and instances narrated in this book eventually merge into one. Each and every one of these commendable scientists relies on the statistical way of thinking, as discrete from everyday thinking. The reader can organize the stories into five pairs, each dealing with an indispensable statistical principle.
What is so eccentric about the statistical way of thinking? First, statisticians do not care much for the accepted concept of the statistical average; instead, they preoccupy on any divergence from the average. They worry about how large these variations are, how often they occur, and why they exist.
In the opening chapter, the experts studying waiting lines explain why we should worry more about the variability of waiting time than about its average. Highway engineers in Minnesota tell us why their preferred tactic to reduce congestion is a technology that forces commuters to wait more, while Disney engineers make the case that the most effective tool to reduce wait times does not actually reduce average wait times. Second, unpredictability does not need to be explained by reasonable causes, despite our natural desire for a rational explanation of everything; statisticians are frequently just as happy to pore over patterns of correlation.
In the second section of the book, the author compares and contrasts these two modes of statistical modeling by trailing disease detectives on the hunt for tainted spinach (causal models) and by prying open the black box that produces credit scores (correlational models). Astonishingly, these practitioners liberally admit that their models are “wrong� in the sense that they do not perfectly describe the world around us; we explore how they justify what they do. Third, statisticians are continually looking out for missed nuances: a statistical average for all groups may well hide vital differences that exist between these groups. Ignoring group differences when they are present frequently portends inequitable treatment. The typical way of defining groups, such as by race, gender, or income, is often found wanting.
In Chapter 3, the book evaluates the mixed consequences that occur when the insurance industry adjusts prices to reflect the difference in the amount of exposure to hurricanes between coastal and inland properties, as well as what happens when designers of standardized tests attempt to eliminate the gap in performance between black and white students. Fourth, decisions based on statistics can be calibrated to strike a balance between two types of errors. Predictably, decision makers have an incentive to focus exclusively on minimizing any mistake that could bring about public humiliation, but statisticians point out that because of this bias, their decisions will aggravate other errors, which are unnoticed but serious.
This framework is employed in Chapter 4 to explain why automated data-mining technologies cannot identify terrorist plots without inflicting unacceptable collateral damage, and why the steroid-testing laboratories are ineffective at catching most of the cheating athletes.
In Chapter 5, we see how this powerful tool was used to uncover extensive fraud in a Canadian state lottery and to dispel myths behind the fear of flying.
These five principles are central to statistical thinking. After reading this book, even a layman like myself, who is far placed from the humdrum of numbers, can use them to make superior judgments.
The ten stories and instances narrated in this book eventually merge into one. Each and every one of these commendable scientists relies on the statistical way of thinking, as discrete from everyday thinking. The reader can organize the stories into five pairs, each dealing with an indispensable statistical principle.
What is so eccentric about the statistical way of thinking? First, statisticians do not care much for the accepted concept of the statistical average; instead, they preoccupy on any divergence from the average. They worry about how large these variations are, how often they occur, and why they exist.
In the opening chapter, the experts studying waiting lines explain why we should worry more about the variability of waiting time than about its average. Highway engineers in Minnesota tell us why their preferred tactic to reduce congestion is a technology that forces commuters to wait more, while Disney engineers make the case that the most effective tool to reduce wait times does not actually reduce average wait times. Second, unpredictability does not need to be explained by reasonable causes, despite our natural desire for a rational explanation of everything; statisticians are frequently just as happy to pore over patterns of correlation.
In the second section of the book, the author compares and contrasts these two modes of statistical modeling by trailing disease detectives on the hunt for tainted spinach (causal models) and by prying open the black box that produces credit scores (correlational models). Astonishingly, these practitioners liberally admit that their models are “wrong� in the sense that they do not perfectly describe the world around us; we explore how they justify what they do. Third, statisticians are continually looking out for missed nuances: a statistical average for all groups may well hide vital differences that exist between these groups. Ignoring group differences when they are present frequently portends inequitable treatment. The typical way of defining groups, such as by race, gender, or income, is often found wanting.
In Chapter 3, the book evaluates the mixed consequences that occur when the insurance industry adjusts prices to reflect the difference in the amount of exposure to hurricanes between coastal and inland properties, as well as what happens when designers of standardized tests attempt to eliminate the gap in performance between black and white students. Fourth, decisions based on statistics can be calibrated to strike a balance between two types of errors. Predictably, decision makers have an incentive to focus exclusively on minimizing any mistake that could bring about public humiliation, but statisticians point out that because of this bias, their decisions will aggravate other errors, which are unnoticed but serious.
This framework is employed in Chapter 4 to explain why automated data-mining technologies cannot identify terrorist plots without inflicting unacceptable collateral damage, and why the steroid-testing laboratories are ineffective at catching most of the cheating athletes.
In Chapter 5, we see how this powerful tool was used to uncover extensive fraud in a Canadian state lottery and to dispel myths behind the fear of flying.
These five principles are central to statistical thinking. After reading this book, even a layman like myself, who is far placed from the humdrum of numbers, can use them to make superior judgments.
April 14, 2018
Great sections on PED tests in cycling and baseball and on polygraph testing. Other sections were a little dry. The book is about statistics though, so don't expect a smooth read.
Regarding baseball, because the USADA/WADA and MLB are so overly paranoid of the false positive drug test, Fung argues that they knowingly use less stringent testing standards. This not only minimizes the number of true positives and false positives, but also increases the false negatives. In other words, more cheaters get off cleanly. This is because overturned false positives humiliate organizations like WADA and diminish their credibility. Of course, the point is well-taken that if the test were only 99% effective, since there are over 700 MLB players, seven innocent players could have their careers ruined.
It does seem as though the science behind these tests hasn't really improved much in the last century. With all the money tied to professional sports and if ensuring the integrity of the game was paramount to all else (maybe it's not), one would think a better, more full-proof test would have been requisitioned long ago. It's also likely that a test of 100% certainty is completely unrealistic.
Additionally, the polygraph testing section highlights the use of polygraphs in Iraq and Afghanistan. It gives some credence to the oft-cited claims that a significant number of insurgents are being held without any evidence of wrongdoing. Because the polygraphs used to process these suspected combatants are setup to minimize the false negative result, Fung suggests that thousands of innocent individuals are implicated for every major security violator correctly identified. In other words, statistically speaking, we're locking up a lot of innocent people just in case.
Regarding baseball, because the USADA/WADA and MLB are so overly paranoid of the false positive drug test, Fung argues that they knowingly use less stringent testing standards. This not only minimizes the number of true positives and false positives, but also increases the false negatives. In other words, more cheaters get off cleanly. This is because overturned false positives humiliate organizations like WADA and diminish their credibility. Of course, the point is well-taken that if the test were only 99% effective, since there are over 700 MLB players, seven innocent players could have their careers ruined.
It does seem as though the science behind these tests hasn't really improved much in the last century. With all the money tied to professional sports and if ensuring the integrity of the game was paramount to all else (maybe it's not), one would think a better, more full-proof test would have been requisitioned long ago. It's also likely that a test of 100% certainty is completely unrealistic.
Additionally, the polygraph testing section highlights the use of polygraphs in Iraq and Afghanistan. It gives some credence to the oft-cited claims that a significant number of insurgents are being held without any evidence of wrongdoing. Because the polygraphs used to process these suspected combatants are setup to minimize the false negative result, Fung suggests that thousands of innocent individuals are implicated for every major security violator correctly identified. In other words, statistically speaking, we're locking up a lot of innocent people just in case.
August 15, 2012
Libro muy, muy interesante en el que en cuatro grandes bloques el autor analiza los usos cotidianos de la estadística, más allá de lo que solemos saber. La estadística se usa cuando aparece un brote epidemiológico, cuando diseñas análisis de dopaje, o exámenes de polígrafo, cuando intentas minimizar los tiempos percibidos por los visitantes de Disneylandia o los viajeros de una red de autopistas, o cuando intentas diseñar un examen tipo test que no discrimine a los estudiantes según su origen. El autor nos muestra bastantes veces que lo que dicta nuestro sentido común es un craso error. He tenido que releer varias veces varios pasajes porque lo que leía me parecía claramente incorrecto, pero resulta que se ha comprobado que hay cosas que son como son a pesar de nuestros prejuicios. El autor se esfuerza en hacernos entender que, por ejemplo, dada una fiabilidad de un test (por ejemplo, el test de dopaje por nandrolona es fiable al 99,9%), cualquier esfuerzo que hagamos por evitar falsos negativos (es decir, por impedir que se escapen los dopados) incrementará el número de falsos positivos (gente limpia que da positivo en el test) y que según el contexto nos interesará más mejorar uno de los dos números (un falso negativo hace trampas pero no sale en los periódicos, un falso positivo es una serie de juicios y portadas en los periódicos criticando el sistema y proclamando su inocencia).
El libro es muy interesante, reitero, y va un paso más allá de la introducción a los temas, siendo en ocasiones lo suficientemente denso como para tener que dedicarle ratillos a digerir las ideas del autor. Acaba el libro con una gigantesca bibliografía comentada que da para cientos de horas de lectura adicional.
Me ha encantado.
El libro es muy interesante, reitero, y va un paso más allá de la introducción a los temas, siendo en ocasiones lo suficientemente denso como para tener que dedicarle ratillos a digerir las ideas del autor. Acaba el libro con una gigantesca bibliografía comentada que da para cientos de horas de lectura adicional.
Me ha encantado.
December 31, 2018
I feel bad giving only one star but this book was dull and not what I expected.
It was a lot of stats (which makes sense when you look at the title!) But the chapters were VERY tedious. It felt like I was reading endless pages of nothing really to get to a conclusion that could have been wrote in a single paragraph 8 pages previously!
There are very few books that I have not been able to finish, I usually push on through to the end even when I find the book most taxing, just to try and be fair when reviewing it.
But I'm afraid I have to admit defeat and admit that I didn't make it to the end of this book.
I was overwhelmed by the droaning, drawn out, prolonged lack of directness and soon realised that I was gaining very little from this book apart from irritation.
So i quit.
If I was studying something relevant to this and I was using it as a study reference book then I am fairly sure that I would have a much more positive review to give.
But for now its time for me to leave this well alone and get back to my fiction book and chill out while i wait for normality to resume after new year madness.
It was a lot of stats (which makes sense when you look at the title!) But the chapters were VERY tedious. It felt like I was reading endless pages of nothing really to get to a conclusion that could have been wrote in a single paragraph 8 pages previously!
There are very few books that I have not been able to finish, I usually push on through to the end even when I find the book most taxing, just to try and be fair when reviewing it.
But I'm afraid I have to admit defeat and admit that I didn't make it to the end of this book.
I was overwhelmed by the droaning, drawn out, prolonged lack of directness and soon realised that I was gaining very little from this book apart from irritation.
So i quit.
If I was studying something relevant to this and I was using it as a study reference book then I am fairly sure that I would have a much more positive review to give.
But for now its time for me to leave this well alone and get back to my fiction book and chill out while i wait for normality to resume after new year madness.
November 3, 2022
I picked up this book at the library and funny enough I’ve only read it when I’m with my client at work while at the library, but it was quite an interesting book. If you’re a fan of Freakonomics, you would definitely be a fan of this book. A lot of the book consists around combining two subjects that have absolutely no relation to each other, like standardized test taking and lie detectors deployed by the US military to find potential terrorists or credit scoring and how people who live inland don’t get the same insurance rates as people who live by the coast. It’s all tied together by statistics and the ways that they are tied together show how some people rely too much on math to find answers, but don’t use there actual experience or common sense to actually get the desired results. At the end of the day, math is just a tool like a hammer, and in the right hands you can create something beautiful, but in the wrong hands you can hurt someone with or without intent! What makes me think is how can a state like Florida even be a Republican state like everyone knows global warming is happening, especially people who live there, so it’s just evil how there government isn’t even trying to mitigate the effects, instead they think they can out maneuver it by creating levees and other means of preventing flooding, which will obviously fail. To some people perception trumps reality but at the end of the day reality will always be there and the math has always been there so when things fail, mathematically speaking, there are usually signs. The coolest part in my opinion was learning about the history of the CDC and how epidemiologists find outbreaks from diseases but in regards to the book, food contamination. Like I can’t imagine how stressful that must be because how short of a time frame you have because if you don’t figure out what food is contaminated, more people will get sick or worse, die. What I found pretty funny is how people in London in the 19th century people thought cholera was caused by something called “miasma� which is essentially just bad air but didn’t think that maybe people were getting sick from dumping literally sewage into the same water they were drinking from and bathing in. You would think things are better now but with covid still rapid and people thinking the vaccine is what causes covid I have little hope in humanity changing even with all the tools we have BESIDES statistics.
April 5, 2020
After reading _Humble Pi_, I pulled this book off of my shelf. Where _Humble Pi_ was funny while describing math disasters, this book takes the opposite approach. It is funny, in a technical way, but also shows when the math actually works. The author gives insight into how numbers can fool us, as us humans are imperfect beings who can over or under think just about everything.
This is a short book, grouped into five chapters. The author is efficient in describing the issue & also telling the stories behind each topic. There is a lot of vindication of the work of engineers and scientists who develop the systems described here. It is a sad state of affairs when politicians who don't know how anything works, demand that the systems that are effective be turned off or scrapped. Then those same politicians demand someone else's head when it goes wrong as predicted.
It wasn't surprising to learn that Disney has scientists who study queues and have figured out how to make waiting in line seem shorter than it really is. This is a common theme throughout the book, as the numbers do not lie. It is the irrational humans who try to make sense of the data and draw false conclusions, seeking patterns where there were none. But with training and discipline the right way forward can be found, though it may not make "common sense".
This is a short book, grouped into five chapters. The author is efficient in describing the issue & also telling the stories behind each topic. There is a lot of vindication of the work of engineers and scientists who develop the systems described here. It is a sad state of affairs when politicians who don't know how anything works, demand that the systems that are effective be turned off or scrapped. Then those same politicians demand someone else's head when it goes wrong as predicted.
It wasn't surprising to learn that Disney has scientists who study queues and have figured out how to make waiting in line seem shorter than it really is. This is a common theme throughout the book, as the numbers do not lie. It is the irrational humans who try to make sense of the data and draw false conclusions, seeking patterns where there were none. But with training and discipline the right way forward can be found, though it may not make "common sense".
February 4, 2020
Fun & Quick read, key takeaways:
The author clearly seeks to defend how statistical methods helped open up the credit facilitation which drove much of recent economic growth. While blind to some segments' needs he demonstrates how it has adavanced the majority of society.
At the same time using the Florida-hurricanes examples he illustrates the limits of statistical models when they simulateaously make some elements unisureable and others irrelevant.
I especially liked the following 2 eyeopeners:
The insight from traffic regulators and Disney that "perception optimisation" is more important than "factual optimisation": people are less concerned with the total time they spend waiting then with what happens while they wait (which makes them forget the wait) and the variance in their waiting.
The insight from exams that "natural" segments like age/gender/race/sex risk to be reinforced if we don't identify each groups high&low perforers and evaluate these within the group rather than cross groups. (Simpson's paradox)
Specificity vs Selectivity trade off : False Negatives vs False Positives : Type 1 or Type 2 errors: the more certain you want to be to exclude all terrorists (when there are few terrorists in a population) the more innocent people you will need to screen out - or the less you can accept to falsely identify someone as doper the less your test can identify every single one who cheats.
The insight that a model doesn't need to be 100% correct to be useful, it just needs to be more efficient than pure chance. You don't have to be right to add value, you just need to be less wrong than the others.
Love Truth - Forgive Error
The author clearly seeks to defend how statistical methods helped open up the credit facilitation which drove much of recent economic growth. While blind to some segments' needs he demonstrates how it has adavanced the majority of society.
At the same time using the Florida-hurricanes examples he illustrates the limits of statistical models when they simulateaously make some elements unisureable and others irrelevant.
I especially liked the following 2 eyeopeners:
The insight from traffic regulators and Disney that "perception optimisation" is more important than "factual optimisation": people are less concerned with the total time they spend waiting then with what happens while they wait (which makes them forget the wait) and the variance in their waiting.
The insight from exams that "natural" segments like age/gender/race/sex risk to be reinforced if we don't identify each groups high&low perforers and evaluate these within the group rather than cross groups. (Simpson's paradox)
Specificity vs Selectivity trade off : False Negatives vs False Positives : Type 1 or Type 2 errors: the more certain you want to be to exclude all terrorists (when there are few terrorists in a population) the more innocent people you will need to screen out - or the less you can accept to falsely identify someone as doper the less your test can identify every single one who cheats.
The insight that a model doesn't need to be 100% correct to be useful, it just needs to be more efficient than pure chance. You don't have to be right to add value, you just need to be less wrong than the others.
Love Truth - Forgive Error
August 26, 2023
An Entertaining Look at an Arcane Subject
This book takes on its subject matter by describing the way statisticians think as they wrestle with real world problems - be it making freeway traffic flow more freely, make credit more readily available to good borrowers, make the SAT tests fairer for students, or ensuring that the food and medicines we take are safe. Looking at these examples makes one realize how much the use of statistics benefits the average person going about his everyday life, without ever realizing the science that underpins these fairly mundane activities.
Fung comes at these problems by describing the way business statisticians think. They worry less about averages than on the deviation from the mean (how large and how frequent), they focus on correlation and causation, they focus on making better decisions rather than perfection.
This book is a refreshingly clear and readable overview of how statistics impacts our dailly lives in a positive way. In the distant days of of the 1980's and earlier so many decisions that affected us were based on gut feel and personal judgment. Given today's plethora of data and cheap computing power we now live in a world of lies, damned lies and sound business decisions!
This book takes on its subject matter by describing the way statisticians think as they wrestle with real world problems - be it making freeway traffic flow more freely, make credit more readily available to good borrowers, make the SAT tests fairer for students, or ensuring that the food and medicines we take are safe. Looking at these examples makes one realize how much the use of statistics benefits the average person going about his everyday life, without ever realizing the science that underpins these fairly mundane activities.
Fung comes at these problems by describing the way business statisticians think. They worry less about averages than on the deviation from the mean (how large and how frequent), they focus on correlation and causation, they focus on making better decisions rather than perfection.
This book is a refreshingly clear and readable overview of how statistics impacts our dailly lives in a positive way. In the distant days of of the 1980's and earlier so many decisions that affected us were based on gut feel and personal judgment. Given today's plethora of data and cheap computing power we now live in a world of lies, damned lies and sound business decisions!
June 30, 2020
I Googled this author and discovered that he's written some posts for the FiveThirtyEight blog (a blog where the writers that applies statistical analysis methods to things like sports and politics). This makes sense, as the book has the same sort of feel to it that the blog does. The author has a good feel for how much depth he should go into when exploring a problem: enough depth to give the reader new insights, but not so much depth that your eyes are glazing over because you've stopped caring.
Two things surprised me about the book: (1) For a book called "Numbers Rule Your World," there were less numbers in this book than I expected. It talks more about statistical concepts, such as variability and DIF analysis, than actual equations. (2) At just under 200 pages, this was a shorter book than I was expecting. (Which, as I have mentioned in other reviews, I appreciate. I respect any author who understands the value of shutting up and declaring a book finished rather than padding the text with another hundred pages of drivel to make the book a standard length.)
Two things surprised me about the book: (1) For a book called "Numbers Rule Your World," there were less numbers in this book than I expected. It talks more about statistical concepts, such as variability and DIF analysis, than actual equations. (2) At just under 200 pages, this was a shorter book than I was expecting. (Which, as I have mentioned in other reviews, I appreciate. I respect any author who understands the value of shutting up and declaring a book finished rather than padding the text with another hundred pages of drivel to make the book a standard length.)
May 26, 2019
In my past life I worked in lending finance. First with consumer finance and then commercial and I saw how banks use statistics and credit scores and standardised testing as lending criteria. That world turned me into an extremely cynical person.
Perhaps not to such an extreme but this book is for the layman who wants to understand these systemised ways. We as consumers need to be aware, aware, and more aware.
This book is not for people who already know how some of it works but I’m concerned that for someone who would really need it might find it a bit over the top. Its pitch level is what kinda put it off, oversimplifying in some parts and too technical in other parts. Towards the end I just skimmed through it.
The book is valuable and a great crash course for a determined individual. My take home from this book to quote from x-files is : trust no one & verify everything.
A solid 3 stars from me for this one.
Perhaps not to such an extreme but this book is for the layman who wants to understand these systemised ways. We as consumers need to be aware, aware, and more aware.
This book is not for people who already know how some of it works but I’m concerned that for someone who would really need it might find it a bit over the top. Its pitch level is what kinda put it off, oversimplifying in some parts and too technical in other parts. Towards the end I just skimmed through it.
The book is valuable and a great crash course for a determined individual. My take home from this book to quote from x-files is : trust no one & verify everything.
A solid 3 stars from me for this one.
December 27, 2017
Quoting the summary of the intent of this book,
"In concluding, I review the five aspects of statistical thinking:
1. The discontent of being averaged: Always ask about variability.
2. The virtue of being wrong: Pick useful over true.
3. The dilemma of being together: Compare like with like.
4. The sway of being asymmetric: Heed the give-and-take of two errors.
5. The power of being impossible: Don’t believe what is too rare to be true."
I skimmed my understanding about how numbers work in our lives and how impactful they are just based on how they look, some are deceptive, some are too true to be ignored.
Statistical thinking is a way in and looking forward for more books like these.
"In concluding, I review the five aspects of statistical thinking:
1. The discontent of being averaged: Always ask about variability.
2. The virtue of being wrong: Pick useful over true.
3. The dilemma of being together: Compare like with like.
4. The sway of being asymmetric: Heed the give-and-take of two errors.
5. The power of being impossible: Don’t believe what is too rare to be true."
I skimmed my understanding about how numbers work in our lives and how impactful they are just based on how they look, some are deceptive, some are too true to be ignored.
Statistical thinking is a way in and looking forward for more books like these.
This entire review has been hidden because of spoilers.
August 8, 2018
I would say this is a very good book for anyone who wants to start on statistics and be hooked on to the subject. Thoroughly analyzing few hand-picked case studies the author does a fabulous job of driving in the influence of numbers, statistics and probability in our daily life. To us SAT may be an examination to judge the student abilities but the tremendous amount of data churned by statisticians to make the examination an unbiased one for all students is not visible to us. Similar is the case of traffic engineers who painstakingly work to make our commute as smooth as possible. Reading this book and getting to know all these case studies was a privilege.
I wrote an extensive review of the book here:
I wrote an extensive review of the book here:
March 12, 2022
This book has been sitting on my shelf for the past four years because I was too intimidated (and concerned about being bored) to bring myself to read it. I ended up being slightly right on both accounts, but once I got into it, the book ended up being a pretty manageable explanation of statistics for the layman. The latter chapters were definitely more interesting than the former, and I particularly liked the section on doping and the section on SAT scores. It was a bit of a chore to read overall, but I definitely learned a few things and really appreciated how Fung tied all of these examples together in the end. I am absolutely not the target for books on statistics, but this wasn’t an awful read.
March 11, 2018
This book perfectly spanned the gap between being too simple for more advanced statistics users, and also not so simple that you could appreciate it as a “fun read�, and as a result ended up missing the mark entirely. The author employs questionable metaphors to “explain� things, and seems to ignore rather than address and counter the most credible arguments against some topics in the book. Moreover, the last chapter and the “crossover� sections read incredibly repetitively, and as though they were deliberately long in order to meet a word count threshold rather than to actually better explain the topic.
July 24, 2021
In-depth analysis of how numbers affect us every day and how they are manifested in common examples.
It provides for a fun read, the likes of Freakonomics, to enlighten how public perception is usually skewed when not taking into account the power of statistics. It clearly shows the importance of them and how we usually either don't understand them or misinterpret them when trying to use them. The athletic drug test and the Disneyland cues were very interesting examples.
All in all, a very good read for those who wish to understand how numbers shape the world we live in.
It provides for a fun read, the likes of Freakonomics, to enlighten how public perception is usually skewed when not taking into account the power of statistics. It clearly shows the importance of them and how we usually either don't understand them or misinterpret them when trying to use them. The athletic drug test and the Disneyland cues were very interesting examples.
All in all, a very good read for those who wish to understand how numbers shape the world we live in.
October 3, 2017
Nothing too Earth-shattering. How stats run our world, how to think about stats in a non "Lies, damn lies, and statistics" mindset, and the five rules of statistical thinking accompanied by some interesting stories to emphasize points. Would probably have been more interesting if we hadn't already read about half of the stories in other books.
April 28, 2018
It said it was probability and statistics for everyday life, but at times it was too nerdy for even me. The author picked some very interesting case studies, certainly ones that many of us can relate to (wait times at Disney, lottery tickets, standardized testing). It was interesting but a bit repetitive. This is not a book I would recommend to just anyone.
April 3, 2020
It was interesting to learn about the influence statistics has on everyday life: insurance, loans, standardised tests. The book is an easy read. He keeps it moving. I'm not a smart person. I felt smarter after reading it.
December 13, 2020
This book was more interesting and easier to read than I expected. Statistics can be an intimidating word but the examples that Fung used were simple enough for even a non-numbers person to understand. It definitely makes you think about everyday events in a different way. I would recommend!
August 29, 2021
What I liked about this book compared to similar economic books is that this one provides a number of success use-cases. It does refer to several other books I've read, so it's really not that far off but also means it doesn't introduce many new concepts or ideas.
February 5, 2022
Holy cow this book was repetitive. I swear I could have written the same ideas in about 50 pages.
Pretty interesting otherwise, didn't learn too much as it was pretty obvious, but I love statistics and math so I found it interesting nonetheless.
Pretty interesting otherwise, didn't learn too much as it was pretty obvious, but I love statistics and math so I found it interesting nonetheless.
Want to read
July 19, 2020elibrary
February 24, 2021
A pretty interesting, if boring book.
July 17, 2023
- deviations from the average are more important than the average
- maybe useful for someone who never heard about statistics and it’s use on predictive models
- maybe useful for someone who never heard about statistics and it’s use on predictive models
Displaying 1 - 30 of 80 reviews
Can't find what you're looking for?
Get help and learn more about the design.