Damned Lies and Statistics: Untangling Numbers from the Media, Politicians, and Activists

by Joel Best

Does the number of children gunned down double each year? Does anorexia kill 150,000 young women annually? Do white males account for only a sixth of new workers? Startling statistics shape our thinking about social issues. But all too often, these numbers are wrong. This book is a lively guide to spotting bad statistics and learning to think critically about these influential numbers. Damned Lies and Statistics is essential reading for everyone who reads or listens to the news, for students, and for anyone who relies on statistical information to understand social problems.

Joel Best bases his discussion on a wide assortment of intriguing contemporary issues that have garnered much recent media attention, including abortion, cyberporn, homelessness, the Million Man March, teen suicide, the U.S. census, and much more. Using examples from the New York Times, the Washington Post, and other major newspapers and television programs, he unravels many fascinating examples of the use, misuse, and abuse of statistical information.

In this book Best shows us exactly how and why bad statistics emerge, spread, and come to shape policy debates. He recommends specific ways to detect bad statistics, and shows how to think more critically about "stat wars," or disputes over social statistics among various experts. Understanding this book does not require sophisticated mathematical knowledge; Best discusses the most basic and most easily understood forms of statistics, such as percentages, averages, and rates.

This accessible book provides an alternative to either naively accepting the statistics we hear or cynically assuming that all numbers are meaningless. It shows how anyone can become a more intelligent, critical, and empowered consumer of the statistics that inundate both the social sciences and our media-saturated lives.

Genres: Nonfiction, Politics, Science, Mathematics, Sociology, Economics, School

190 pages, Hardcover

First published November 1, 1998

Reviews

[G.R. Reader · Rating 3 out of 5]

I don't want to sound like I'm questioning Goodreads's figures. All the same, the number of people listed as having Off-Topic on their to-read shelf might possibly be an underestimate.

UPDATE, NOV 29 2013



Thank you for fixing that, Goodreads. We maybe don't agree on everything, but I appreciate your sense of fair play here.

UPDATE, DEC 8 2013

As Cecily points out below:

Given the number of people that said they had voted for this in the GR Choice Awards, and the number who have rated and reviewed it, I was surprised to see that the non-fiction book that came 20th had only 145 votes, and yet this wasn't listed:

https://www.goodreads.com/choiceaward...

I guess some voted for it in the Debut Author category (20th place had more than 600 votes), but not non-fiction.

Like Cecily, I doubt that anything untoward happened here. But given that Goodreads have already made one careless error with the statistics for my book, wouldn't it be sensible for them to post the number of votes it got, so that everyone could tell the conspiracy theorists to go take a cold shower and calm down?

[Manny]

There has been a great deal of discussion recently about how many people there really are on Goodreads. The official number is 20 million. I'm in no way disputing that 20 million accounts have been opened. On the other hand, this figure isn't very interesting. I know many people who have opened an account, looked around for a few minutes, and decided that this wasn't for them. I also discovered last week, when I was gathering data about the downvoting campaign that was being run against Off-Topic, that it is ridiculously easy to open a sockpuppet account. Unless the rules have changed since then, you don't even need a valid email address; it literally takes one minute to log in with a fake address and post a rating. I very much doubt that I am the only person who has tried this.

So: how many real users are there on Goodreads, meaning members who post on the site regularly? I don't know, but you may want to check out this Wikipedia page I was just looking at. It says that there are about 20 million named accounts on Wikipedia, a figure close to the one quoted for Goodreads. However:

- only about 300,000 people have made a total of more than 10 edits;

- only about 30,000 people make more than five edits during a typical month;

- only about 3,000 people make more than 100 edits during a typical month.

This page lists the Wikipedians with the highest numbers of edits. If it's correct, there are, again, only about 3,000 people who have made a total of more than 20,000 edits.

Obviously, you can argue about all these figures. (They explicitly warn you to take them with a large grain of salt). But the bottom line seems to be that the core Wikipedia community is in fact quite small, and consists of just a few thousand members.

[Kat · Rating 4 out of 5]

3.5 stars. If you’ve taken any classes on statistics, this may seem quite basic but I still think it’s a good guide to thinking about social statistics.

[فهد الفهد · Rating 3 out of 5]

افتراءات لعينة وإحصائيات

وصلت إلى مرحلة الشك العميق بكل إحصائية أجدها أمامي، وهذا الكتاب ينمي هذا الشعور، لقد كانت الإحصائيات والدراسات نوع من القفلة لأي حوار مفتعل – وما أكثرها في مجتمعنا -، عندما يكون بيدك إحصائية فأنت عندها أقوى حجة وموقف من غريمك، ولكن هذا الكتاب وكتب أخرى مماثلة تعلمك أن الإحصائيات ليست علماً خالصاً، وإنما يمكن لها أن تصبح أداة سياسية، فلذا في كل مرة تجد فيها إحصائية أمامك فكر أولاً: من قام بها؟ لماذا قام بها؟ ومن المستفيد؟

يعالج المؤلف بعض الإحصائيات المنتشرة في أمريكا، ويحاول إظهار عيوبها والأخطاء المنهجية التي وقع فيها معدوها.

[Gustavo Garcia · Rating 5 out of 5]

I wish everyone who shares posts with statistics and numbers on social media, specifically Facebook, and/or physical platforms to give a read to this book. We tend to take numbers as facts and forget they were constructed through the conceptual ideologies of a person. We ought to understand what we are reading and how do we interpret it.

I will like to finish by sharing a quote from the book I consider essential:

'Reality is complicated, and every statistic is someone's summary, a simplification of that complexity' (p.161)

[Steve · Rating 4 out of 5]

Statistics are constructed not discovered. It is people that create statistics, consequently statistics are coloured by the worldview of the constructor. There is no such thing as a neutral statistic. This book provides ample evidence that statistics are the products of social activity. Joel Best, a professor of sociology and criminal justice, has produced a readable and informative book. He draws upon statistics from many walks of life to illustrate his points.

Those who create statistics want to prove something. Best, shows how by asking key questions we can help expose these underlying perspectives:

Who created the statistic?
Why was this statistic created?
How was the statistic created?

Best deals with key issues such as the source of bad statistics: bad guesses, descriptive definitions, confusing questions and biased samples; mutant statistics: the ways in which good statistics can be mangled, misused and misunderstood; and the problems of statistical comparison. It requires no background in maths or statistics. It will help readers be more critical in their acceptance of statistical data.

[Drtaxsacto]

I first read this when I started my doctoral work and rediscovered it. His basic point is that statistics serve a purpose but be careful that you try to understand the purpose. He discusses in the final chapter the naive, the cynical and the critical - three types of statistics users. He supports being a critical consumer of numbers.

He also has lots of examples of statistics used for nefarious purposes as well as those statistics that no one has ever bothered to question which may have been created by someone who does not understand numbers or accepted the word of others uncritically.

This was well worth reading AGAIN.

[Julianna Hillman · Rating 1 out of 5]

thank god this class is over

[Alexandru · Rating 5 out of 5]

A great addition to the "How to lie with statistics" book, since one focuses on mathematical tricks more and this one is more focused on definitions and biases involving statistical research. It analyses the main reasons why statistical information is mishandled and used for various social causes and why exaggerations and plainly wrong info is distributed as official statistics around us. The author calls us to be critical and avoid nativity or cynicism when shocked by surprising statistical conclusions. In other words, a healthy degree of scepticism is always the way to digest data, since it got an almost magical or fetishised status in today's world. I don understand why some reviewers are angry with the book - it shakes the ground of a lot of bold claims that were made for political or social agendas.

My favourite quotes from the book that I liked:
1. No statistic is perfect, but some are less imperfect than others, Good or bad, every statistic reflects its creators' choices.
2. Activists use statistics to convenience us that social problems are serious and deserve out attention and concern. Charities use statistics to encourage donations. Politicians use statistics to persuade us that they understand society's problems and that they deserve our support. The media uses statistics to make their reporting more dramatic, more convincing, more compelling. Corporations use statistics to promote their products and improve their profits. Researchers use statistics to document their findings and support their conclusions. Those with whom we agree use statistics to reassure us that we're on the same side, while our opponents use statistics to try and convenience us that we are wrong.
3. A perfectly free society is not likely to be especially egalitarian, nor is a perfectly egalitarian society likely to be especially free.

[Bob Wallner · Rating 4 out of 5]

May 2016 Re-Read Review
I listened to this book and was amazed going how relevant this book is, especially in an election year with candidates touting how many illegal immigrants there are or how many poor/rich there are. Makes you wonder where these statistics come from!!!!


October 2015 Review
I really wasn't sure what this book was going to be about.

I thought it may be about how to use statistics to lie or cheat. The author does recognize that statistics can be used for ill gotten purposes, but his main purpose is to get his readers to not take statistics for granted. Take the time to really think about what the statistic means and is the statistic realistic. In his opening he quotes a "mis-written" statistic. This stat has been misquoted for so long it is taken as fact, but when you sit down and think about what it is saying, you see how ludicrous it sounds.

Even though the spoke is specifically about social statistics, anyone who deals with statistics will find something practical contained within its pages or audio.

[Maria · Rating 3 out of 5]

The points in this book can be summed up quickly:
* Society as a whole is innumerate (with caveats)
* Statistics can be misunderstood, misquoted, over- or undergeneralized, and these issues can all be compounded.
* All creators of statistics have their own agenda, even if it is that their statistics be unbiased.
* When looking at a statistic, think critically about it: who created it, with what intent, how?

There were so many and varied examples, which perhaps would have been useful had I known any of them previously. The repetition on certain points made me wonder if this needed to be a book in the first place, instead of just being a long newspaper article.

[Jared · Rating 5 out of 5]

While the book is not perfect, it teaches very important concepts about understanding statistics, especially as used by activists and media. It's very readable; maybe a bit "too readable" for someone with multiple statistics classes but it deals with applied (lay) statistics better than any other book I've read. Reading this book can help you be more critical of your interpretation of statistics, which is really its most important goal - critical thinking.

[Roger Blakesley · Rating 4 out of 5]

Read this in 2005 and loved it. It is more important, not for the statistically literate, but an helpful guide to see where the errors of the media, the Government, and advertisers or educators are trying to forward their biases or hide their weaknesses behind arguments.

I gave it a brief re-read this month when Best's traditional interviews about poisoned Halloween candy came out. (There isn't any poisoned Halloween candy.)

[Shawn · Rating 3 out of 5]

Another good book to give one a better feel for the use of statistics in popular debate.

[Richard]

How easy it is to be deceived by statistics.

[Michael Green · Rating 4 out of 5]

An informative, eye-opening book that delivers on its premise to challenge entrenched ideological prejudices rooted in “innumeracy” (an inability to correctly interpret quantitative data). Best was especially skilled in presenting subjects in a way that avoided obfuscation while still making clear his expertise as a sociologist and researcher.

The final chapter is the best in the book, as it really drives home the point that statistics are created, disseminated, and interpreted by human actors and therefore subject to many of the same flaws found in qualitative analyses. His clarion call to avoid cynicism was especially useful given the largely unnerving nature of the text, and Best instead advocates for a “critical” approach that embraces healthy skepticism while also avoiding the all-too-common pitfall of false balance (believing that a viewpoint is legitimate solely because it appears to be in the middle of two opposing viewpoints).

The only reason I gave this text four instead of five stars is because I felt that the last one or two chapters felt rushed and could have contained many more examples and analysis. Perhaps the author did not wish to make the book excessively lengthy (from what I’ve seen on Goodreads there appears to be a sequel text), but it’s nevertheless disappointing for me to see an expert in a field lay down a significant thesis and only expound it for twenty-some pages. Otherwise, this was a great read!

[Emily · Rating 5 out of 5]

This book was a quick read and very useful. I knew a fair amount about statistics coming in, yet I already find myself reading newspapers and magazines in a very different way. I'm shocked at how frequently numbers and statistics are being used to obfuscate and manipulate (even if well-meant) instead of to inform.

Some reviewers complained that the book was repetitive, but I think the structure was useful because the author used different examples to show various ways similar statistical tricks or methods could deceive. I read a number of the examples aloud to my husband (an astrophysicist with a specialty in Bayesian statistics), and he was even surprised a few times.

I plan to have my kids read this during high school.

[Lauren Mintz · Rating 4 out of 5]

I had to read this book for a class but it’s actually very interesting!!! if you want a good perspective on numbers and stats that you hear daily & how to think abt them & interpret what they mean definitely read this book! and the author does a great job of making the book easy to read and interesting so you don’t feel like your just reading about statistics … because that would be boring. & that’s what i thought this book would be but I actually enjoyed it & learning what the book had to offer about everyday reported stats numbers

[Fernando Bragança · Rating 3 out of 5]

This book is a guide to understanding how statistics are often misused, intentionally or not, by the media, politicians, and advocacy groups. Best doesn’t just point fingers; he explains how and why these distortions happen, and how we can become more informed consumers of data.

"Damned Lies and Statistics" is for anyone who wants to be a more informed citizen. Joel Best doesn’t just teach you how to spot bad statistics; he helps you appreciate the value of good ones. It’s a smart, eye-opening book that will forever change the way you read the news and engage with public discourse.

[Ilinca · Rating 5 out of 5]

Extremely interesting and incredibly short. I thought I was just getting started, then it ended. Together with The Signal and the Noise, these are essential readings for someone looking for a quick, fun intro to how statistics and data science are both awesome and misused or misunderstood. But then there's nothing very substantial. Still, five stars because I enjoyed it and it does the job of making you curious and aware.

[Will · Rating 4 out of 5]

I can't go into specific details as it's been a while, but I enjoyed this book. This book debunks a lot of facts that we believe to be true. For example, "10% of people are gay," comes from a biased study from before World War II, when it's closer to 3%. I liked that this book attacked both liberal and conservative statistics. This book also explains how statisticians become corrupt and the best ways to read and interpret them.

[Nightkid · Rating 5 out of 5]

　　某日在圖書館巡梭時，眼角餘光不小心瞄到此書，立刻被書名誘惑了。
　　基於工作的綠故，幾乎每星期都有機會接觸民意調查報告，雖然我過去從未接受過正式的統計學課程，亦足以憑經驗歸納出幾個看法。
　　誠然，不論是大學、政府、醫療團體或各大智庫，他們都因著各自的既定立場，製作符合其利益的調查報告。相同的數據，若由不同團體來解讀，結果亦相去甚遠，尤其涉及政治考慮時，情況特別明顯。
　　作者在字裡行間，彷彿在暗示媒體就是導致突變統計的元凶－－雖然符合現況，但卻是社會大環境造成的。媒體對「數字」必須敏感，尤其涉及現有人口比例、預測等情況時，總希望某學者能提出精確或猜測的數目。說穿了，這不過是一個讓讀者形象化的過程罷了，只求達到加深讀者印象的目的。

[Dana Robinson · Rating 5 out of 5]

A really important book about statistics that focuses more on the social construction of numbers rather than numerical or graphical trickery. An incredibly important read for anyone involved in data science while remaining accessible to laypeople. Chapter 6 is a little awkward, with its strawman 'categories', but the rest of the book is excellent.

[troy pike · Rating 3 out of 5]

Not sure how I feel about this book.

I guess I fall in the category of what the author calls a critical thinker when it comes to numbers. I thought a lot of people were like this, but after reading this I realize that may not be the case. This helped me realize how peoples biases can be the better of them, even though any I have don’t. I’m giving it 3 stars.

[John · Rating 2 out of 5]

Overly repetitive. Great concept that lacks any real compelling digging into that concept. Peppered with terms that get defined every 4 pages in case we forgot what they mean with our assumed 4th grade reading level. My biggest complaint is that I was actually really excited for this book.

[Amber Taylor · Rating 5 out of 5]

An interesting book on how we should be more critical of statistics presented as fact, and how we can be more mindful when questioning suspect statistics.

Note: This book does NOT say all statistics are bad. It says we need better quality statistics.

[Hannah · Rating 4 out of 5]

Not sure why this has under four stars. It is a great book to read to understand how to think about statistics and to approach data. I work in a data heavy field and see people making up crazy stats and numbers to receive credit for things or tell stories that just aren’t real.

[Kelly · Rating 4 out of 5]

Solid primer on being an informed consumer of statistics. It's a little repetitive, and its age shows in some of the language used around social issues, but still worth a read. I'm planning to assign parts of it to my grad students this semester.

[Dick Hamilton · Rating 4 out of 5]

Excellent book that does not use a lot of math but provides input to the reader on how to interpret and question statistics that are presented in relation to social problems. Good insight for the casual reader.

[Jocelin · Rating 2 out of 5]

The novel by Joel Best was very informative and interesting in the beginning, but then it just got repetitive as the chapters went on and I just found myself dreading throughout the pages.