Extra Damned Lies and Statistics: How Numbers Confuse Public Points
By Joel Greatest
College of California Press
Hardcover, 217 pages
ISBN: 9780520238305
September 2004
$29.95, £19.95
My Ranking: 3/5
Introduction
On this new world of Massive Knowledge, Knowledge Science, and the computing energy of a 1980’s Cray supercomputer in each pocket, we’re inundated with increasingly statistics and mathematical fashions primarily based on increasingly “information.” This torrent of actual science and pseudoscience (generally formally sanctioned) contains the doubtful monetary fashions that contributed to the 2008 monetary crash and “Nice Recession,” world local weather fashions used to induce us to desert oil and pure gasoline in favor of austerity or vaguely outlined various vitality applied sciences, complicated statistics used to persuade us to get flu vaccinations that regularly don’t work, statistical claims of small enhancements in common life expectancy from chemotherapy that lead hundreds of thousands of terminal most cancers sufferers to pay tons of of 1000’s of {dollars} and endure monumental ache from “medication” that may be labeled as deadly poisons in nearly every other context, and plenty of different examples. In all of those examples, authorities officers and businesses have given implicit or specific help for the statistics and fashions: Alan Greenspan and the Federal Reserve, NASA and former Vice-President Al Gore amongst different political leaders, the Facilities for Illness Management (CDC), and the Nationwide Institutes of Well being (NIH).
How are we as residents and customers to make sense of those statistics and mathematical fashions? Sarcastically, the usual likelihood and statistics taught in faculties and in AP Statistics at the highschool degree in the USA is insufficient, mandatory however not enough to critically analyze these typically costly and eye-popping claims. The reader can take the usual programs (I’ve), grasp the intricacies of Bayesian versus frequentist statistics, obtain and grasp the free R programming language utilized by skilled statisticians, learn and reread each Wikipedia entry on likelihood and statistics and nonetheless be bamboozled. Why? Actual statistics and mathematical fashions are created by actual, fallible, grasping, bold, fearful, indignant human beings and these human failings seem most frequently within the definition of what’s counted, how it’s counted, the choice and sampling of the information, the interpretation and presentation of the outcomes, and generally in dishonest.
To know and detect these issues with actual statistics and actual mathematical fashions, we have to look past the dry tutorial literature on likelihood and statistics to works like Darrell Huff’s basic The best way to Lie with Statistics.
Extra Damned Lies and Statistics is the 2004 sequel to Professor Greatest’s Damned Lies and Statistics which I reviewed a couple of weeks in the past. Extra Damned Lies and Statistics offers extra examples of the misuse of statistics within the 1980’s, 1990’s, and early 2000’s together with some dramatic examples of the strategic omission of statistics which may put a declare in a a lot totally different perspective.
Total, Extra Damned Lies and Statistics is an efficient guide, however not the nice guide that Damned Lies and Statistics is, repeating various factors from the primary guide and likewise various factors from The best way to Lie with Statistics. One of many issues that I appreciated concerning the first guide is that it enhances The best way to Lie with Statistics with new and totally different insights.
Sturdy First Chapter
Extra Damned Lies and Statistics begins with a robust first chapter which is on the market without spending a dime on the College of California Press website for the guide (on the time of penning this overview). Studying the free first chapter led me to purchase the entire guide. The later chapters are good, however not on the degree of the primary chapter or the primary guide.
Extra Damned Lies and Statistics begins with a bang: the “epidemic” of college shootings within the 1990’s culminating within the April 20, 1999 Columbine Excessive College capturing in Littleton, Colorado. Professor Greatest proceeds to quote statistics exhibiting that college shootings of every type are each extraordinarily uncommon and really declined throughout the 1990’s.
For instance, there have been a complete of twenty-five (25) violent faculty deaths in 1999 together with the Columbine deaths, down from forty-four (44) in 1993. America Census claims there have been about 51.2 million college students enrolled in colleges (nursery faculty by way of twelfth grade) in October 1999.
In his first guide, Professor Greatest offers many examples the place a giant quantity, typically a million or extra, primarily based on a guess or broad definition of a social downside was mixed with uncommon, horrific examples of the issue to create a deceptive if not false image of the issue: one-million lacking youngsters and the horrific abduction and homicide of six-year outdated Adam Walsh in 1981. Within the case of college shootings, no statistics got though phrases like “epidemic” have been utilized by commentators reminiscent of Dan Slightly. Even a broad definition of college shootings offers a small quantity, a lot lower than one-million.
Extraordinarily uncommon examples could be extremely deceptive and are widespread within the mass media, self-help books, speeches by politicians, and various different extensively obtainable sources of data.
The Mass Media as Funhouse Mirror
Traditionally, the mass media referred to nationwide tv networks (ABC, CBS, NBC, and PBS in the USA, the BBC within the UK), main and more and more nationwide and even worldwide newspapers such because the New York Instances and the Wall Road Journal, and extensively distributed magazines reminiscent of Time and Newsweek. More and more the mass media is shifting to the Web and incorporating search engines like google, particularly the market chief Google, and sure websites reminiscent of Wikipedia that regularly seem within the high hits from a Google search. Practically the entire mass media is closely or fully funded by promoting. Purely subscription-based fashions during which the top person pays are uncommon. He who pays the piper, calls the tune.
Each of Professor Greatest’s books illustrate the extent to which what we see, hear, and skim within the mass media is sort of a funhouse mirror. Some points and occasions are blown up approach out of proportion to their precise dimension. Others are shrunken and squashed. Some points and occasions are offered precisely. Some are closely distorted. Some points and occasions are fully pretend. Some actual issues usually are not proven within the mirror in any respect.
These issues usually are not more likely to lower within the Massive Knowledge period when the era of deceptive or false statistics could be automated and “personalised,” personalized on a per-viewer foundation to attraction to our particular person prejudices, biases, and cognitive weaknesses. Quickly enhancing audio and video, pc generated imagery, and digital actuality applied sciences are making the distorted pictures within the funhouse mirror extra plausible and emotionally interesting, extra actual than actual — hyperreal as some name it.
Freely obtainable open-source applications such because the R programming language comprise few if any instruments for detecting the kind of errors or manipulations of knowledge and evaluation chronicled in Professor Greatest’s books. Utilizing Google or different search engines like google to trace down unique information and critically analyze some declare could also be troublesome or not possible if Google (for instance) is selling the declare. Comparable feedback apply to different main info providers reminiscent of these provided by Microsoft, Yahoo, Netflix (take into account the documentaries pushed by Netflix), and different main Web/pc corporations.
Unplugging from the Matrix
Whereas Professor Greatest’s books do a great job of exhibiting the reader what to search for in errors or deliberate manipulations of statistics, he doesn’t present a lot sensible recommendation on how time-strapped readers can successfully analyze the various statistics and mathematical fashions that we’re more and more inundated with within the trendy world. As I’ve famous, counting on Google, the present default for many individuals, and Wikipedia, which regularly turns up within the high few hits from Google and different search engines like google, has apparent limitations. In his first guide, Professor Greatest gave no sensible recommendation on this necessary subject.
In Extra Damned Lies and Statistics: How Numbers Confuse Public Points Professor Greatest does embody a listing of websites that critique and assist analyze statistics (circa 2004). Nevertheless, this can be a fairly quick laundry listing of websites within the remaining chapter which is usually dedicated to arguing for instructing “statistical literacy” in colleges and faculties.
Most of us lack the time and assets to conduct the usual analyses that Professor Greatest, a talented tutorial, has carried out on a number of points reminiscent of lacking youngsters and that may be, probably, taught in a statistical literacy course. It isn’t merely a matter of figuring out tips on how to critically analyze statistics and mathematical fashions which might be used to advertise public insurance policies reminiscent of vaccination or wars but in addition items and providers reminiscent of mortgages, medication and medical therapies. Additionally it is a query of time, cash, and different assets.
To safeguard our personal pursuits and well-being, to be good residents and make the world a greater place, we want sooner and cheaper strategies and instruments to guard in opposition to the kind of mistaken, deceptive, and even fraudulent statistics described in Damned Lies and Statistics and Extra Damned Lies and Statistics.
Conclusion
Extra Damned Lies and Statistics is an efficient guide however not a fantastic guide. If you need to select between this guide and the primary guide Damned Lies and Statistics, I’d suggest the primary guide. If I might solely afford two books on the topic, I’d get Darell Huff’s The best way to Lie with Statistics and Damned Lies and Statistics. These two complement one another effectively (learn The best way to Lie with Statistics first if you’re new to the topic). Extra Damned Lies and Statistics expands upon a few of the factors in Damned Lies, introduces a couple of new factors, however repeats lots from Damned Lies and The best way to Lie with Statistics with some new examples.
The world remains to be ready for a great guide or open supply software program program, or maybe mixture of the 2, to critically analyze the rising torrent of Massive Knowledge fueled statistics and mathematical fashions.
© 2015 John F. McGowan
Concerning the Creator
John F. McGowan, Ph.D. solves issues utilizing arithmetic and mathematical software program, together with growing video compression and speech recognition applied sciences. He has intensive expertise growing software program in C, C++, Visible Fundamental, Mathematica, MATLAB, and plenty of different programming languages. He’s in all probability greatest recognized for his AVI Overview, an Web FAQ (Continuously Requested Questions) on the Microsoft AVI (Audio Video Interleave) file format. He has labored as a contractor at NASA Ames Analysis Middle concerned within the analysis and growth of picture and video processing algorithms and know-how. He has printed articles on the origin and evolution of life, the exploration of Mars (anticipating the invention of methane on Mars), and low cost entry to area. He has a Ph.D. in physics from the College of Illinois at Urbana-Champaign and a B.S. in physics from the California Institute of Expertise (Caltech). He could be reached at [email protected].
![Erratum for “An inverse theorem for the Gowers U^s+1[N]-norm”](https://azmath.info/wp-content/uploads/2024/07/2211-erratum-for-an-inverse-theorem-for-the-gowers-us1n-norm-150x150.jpg)
