The Signal and the Noise: The Art and Science of Prediction

The Signal and the Noise: The Art and Science of Prediction

  • Downloads:5899
  • Type:Epub+TxT+PDF+Mobi
  • Create Date:2021-06-12 09:55:53
  • Update Date:2025-09-06
  • Status:finish
  • Author:Nate Silver
  • ISBN:0141975652
  • Environment:PC/Android/iPhone/iPad/Kindle

Summary

One of Wall Street Journal's Best Ten Works of Nonfiction in 2012

New York Times Bestseller

"Not so different in spirit from the way public intellectuals like John Kenneth Galbraith once shaped discussions of economic policy and public figures like Walter Cronkite helped sway opinion on the Vietnam War…could turn out to be one of the more momentous books of the decade。"
-New York Times Book Review

"Nate Silver's The Signal and the Noise is The Soul of a New Machine for the 21st century。"
-Rachel Maddow, author of Drift

"A serious treatise about the craft of prediction-without academic mathematics-cheerily aimed at lay readers。 Silver's coverage is polymathic, ranging from poker and earthquakes to climate change and terrorism。"
-New York Review of Books

Nate Silver built an innovative system for predicting baseball performance, predicted the 2008 election within a hair's breadth, and became a national sensation as a blogger-all by the time he was thirty。 He solidified his standing as the nation's foremost political forecaster with his near perfect prediction of the 2012 election。 Silver is the founder and editor in chief of FiveThirtyEight。com。

Drawing on his own groundbreaking work, Silver examines the world of prediction, investigating how we can distinguish a true signal from a universe of noisy data。 Most predictions fail, often at great cost to society, because most of us have a poor understanding of probability and uncertainty。 Both experts and laypeople mistake more confident predictions for more accurate ones。 But overconfidence is often the reason for failure。 If our appreciation of uncertainty improves, our predictions can get better too。 This is the "prediction paradox": The more humility we have about our ability to make predictions, the more successful we can be in planning for the future。

In keeping with his own aim to seek truth from data, Silver visits the most successful forecasters in a range of areas, from hurricanes to baseball, from the poker table to the stock market, from Capitol Hill to the NBA。 He explains and evaluates how these forecasters think and what bonds they share。 What lies behind their success? Are they good-or just lucky? What patterns have they unraveled? And are their forecasts really right? He explores unanticipated commonalities and exposes unexpected juxtapositions。 And sometimes, it is not so much how good a prediction is in an absolute sense that matters but how good it is relative to the competition。 In other cases, prediction is still a very rudimentary-and dangerous-science。

Silver observes that the most accurate forecasters tend to have a superior command of probability, and they tend to be both humble and hardworking。 They distinguish the predictable from the unpredictable, and they notice a thousand little details that lead them closer to the truth。 Because of their appreciation of probability, they can distinguish the signal from the noise。

With everything from the health of the global economy to our ability to fight terrorism dependent on the quality of our predictions, Nate Silver's insights are an essential read。

Download

Reviews

Monika

PQHS 432

Brent Saindon

The book is an impressive exercise in thinking about probability and prediction across a number of domains。 I'm not sure that the last half fully delivers on its promises, but it was an insightful read nonetheless。 I'm sure there are many errors in the book, as with any pop press book that attempts to work through academic material, but since these are not my fields, I cannot say for certain。 The book is an impressive exercise in thinking about probability and prediction across a number of domains。 I'm not sure that the last half fully delivers on its promises, but it was an insightful read nonetheless。 I'm sure there are many errors in the book, as with any pop press book that attempts to work through academic material, but since these are not my fields, I cannot say for certain。 。。。more

Florence

This book revolves around one idea: human intuition is flawed but it's indispensable in making meaningful predictions from statistical models。 A combination of the two will always outperform either。Some feedback on this book is that it's just chapters after chapters of the same point (isn't that most non-fiction?), but that's what I like about it: Being introduced to a new domain, diving deep into the anecdotes, and learning something new every other page。 It requires focus and dedication to und This book revolves around one idea: human intuition is flawed but it's indispensable in making meaningful predictions from statistical models。 A combination of the two will always outperform either。Some feedback on this book is that it's just chapters after chapters of the same point (isn't that most non-fiction?), but that's what I like about it: Being introduced to a new domain, diving deep into the anecdotes, and learning something new every other page。 It requires focus and dedication to understand some ideas, but they're all very interesting so definitely worth it。Love this book but would only recommend to those who are ready to do some deep thinking。 。。。more

Wayne Webb

Fascinating and easy to follow if a little dense and slow in places。 Some very good pieces followed up by exacting details but then swerves into Opinion just as quickly。 On the whole the premise is sound。 The irony here is that reading this book you have to distinguish the signal from the noise, not that often mind you。 But more than once。 Definitely worth reading with the same critical eye he recommends。

Mike Hewitt

I've been reading this for several years now and just finally finished it。 There were some very important ideas expressed here, but I think it was just too darn long。 And personally I'm not into sports so those sections were a slog for me。 I've been reading this for several years now and just finally finished it。 There were some very important ideas expressed here, but I think it was just too darn long。 And personally I'm not into sports so those sections were a slog for me。 。。。more

Bret Eubank

Thorough, thought-provoking, insightful and entertaining。

Jumax9

La verdad es que el libro está bastante bien, es un poco un compendio de predicciones (y la falta de ellas), entrevistas a personajes relevantes en cada caso (desde ¿se pueden predecir terremotos? a ¿podíamos haber visto venir el 11-S?) y reflexiones al respecto。La verdad es que tan el estilo como la forma de escribirlo no es muy diferente de leer un blog, es bastante entretenido y Nate Silver es bastante inteligente así que también es interesante e informativo。Por el lado negativo, Nate Silver La verdad es que el libro está bastante bien, es un poco un compendio de predicciones (y la falta de ellas), entrevistas a personajes relevantes en cada caso (desde ¿se pueden predecir terremotos? a ¿podíamos haber visto venir el 11-S?) y reflexiones al respecto。La verdad es que tan el estilo como la forma de escribirlo no es muy diferente de leer un blog, es bastante entretenido y Nate Silver es bastante inteligente así que también es interesante e informativo。Por el lado negativo, Nate Silver es un notas y pasa una parte importante del libro dejando claro lo listo e inteligente que es y cuánto se gusta a sí mismo。 No como otros。 Muchos errores son obvios para su excelencia Nate。 En particular está esta cosa sobre zorros y erizos (https://en。wikipedia。org/wiki/The_Hed。。。) con la que da un por saco impresionante。。。En resumen, una vez uno es capaz de pasar esta manta de egolatría que tiene el libro, es una lectura bastante interesante y entretenida。 Si no, puede hacerse pesado。 。。。more

Nicholas Garcia

Solid in every way。 Contains fascinating insights about why and how we make the predictions we do, and encourages us to do something about them。

Quinn Rhodes

Best book I've read this year Best book I've read this year 。。。more

Jurij Fedorov

1。 A CATASTROPHIC FAILURE OF PREDICTION6/10It's a good chapter。 It's a good intro to predictions and how most of them fail。 It largely focuses on the housing bubble and also mentions that no one predicted the fall of USSR or any other recent nation。It's just very basic。 Both the intro and the first chapter are great for the right reader, but any politically minded person who is not brain damaged by watching CNN or Fox News already knows most pundits are terrible at predicting things。2。 ARE YOU S 1。 A CATASTROPHIC FAILURE OF PREDICTION6/10It's a good chapter。 It's a good intro to predictions and how most of them fail。 It largely focuses on the housing bubble and also mentions that no one predicted the fall of USSR or any other recent nation。It's just very basic。 Both the intro and the first chapter are great for the right reader, but any politically minded person who is not brain damaged by watching CNN or Fox News already knows most pundits are terrible at predicting things。2。 ARE YOU SMARTER THAN A TELEVISION PUNDIT?6/10Foxes and hedgehogs。 Never liked the terms and find them to be childish, silly and even misleading。 I get why he would use them, but it doesn't quite work。 The chapter is strong though。3。 ALL I CARE ABOUT IS W’S AND L’S6,5/10Very shallow overview over moneyball in baseball。 It's a fine short intro, but the point is that moneyball is not in any way perfect and that stats change and adapt。 Good chapter though。4。 FOR YEARS YOU’VE BEEN TELLING US THAT RAIN IS GREEN6/10About earthquakes。 Fine intro, nothing more。5。 DESPERATELY SEEKING SIGNAL6/10Weather。6。 HOW TO DROWN IN THREE FEET OF WATER6/10Economics and biases。 Nothing deep。7。 ROLE MODELS5,5/10Flu predictions fail。 It's a shallow overview。 Not really sure what I truly remember from this chapter even after having listened to it twice。 Flu predictions are just terribly wrong, but I do need examples of failures to understand his points clearly。8。 LESS AND LESS AND LESS WRONG6/10Predictions and how to adjust to them。 Fine intro, nothing more。9。 RAGE AGAINST THE MACHINES6/10About chess AI。 It's fine。 It's stuff you know if you have watched a Deep Blue documentary。 There is a long YouTube video about it。10。 THE POKER BUBBLE6,5/10Poker chapter。 Fine intro to the topic, but it's kinda too simple。 Nothing much to learn here in my opinion。 It's also hard to understand the details about the game itself。11。 IF YOU CAN’T BEAT ’EM 。 。 。6/10Stock trading。 Again a dry by the numbers chapter that tackles the basics。 This is a great chapter/book for people who don't know about this stuff, but to me it feels very unfocused。 There is not much new to learn for people who already understand big data as it's not a book for us。 It's also very careful and scientific so you don't really get big statements。 Rather all chapters are about stuff all intellectuals more or less agree on; this is good, but kinda predictable and dry。I frankly don't have much want to reread many of the chapters which to me illustrates that the book didn't fully grab my attention。 I'll reread/relisten to the flu chapter though as I forgot what examples it used。12。 A CLIMATE OF HEALTHY SKEPTICISM7/10Very good chapter on climate change and how many completely overestimate how huge an influence it plays。 Still very word heavy instead of always being convincing。13。 WHAT YOU DON’T KNOW CAN HURT YOU6,5/10Terrorism。 It's a very good intro to the subject。 But I knew most of it already。 Still, these single chapters could easily be text you read at universities about these subjects。 Incredible fast overviews and nearly all completely unbiased as far as I can see。My final opinion on the bookThis is a book that never really goes in-depth on any one subject, but these chapters are some of the very best intros to the topics you can find。 If you really don't know much about data research this book will blow your mind。 If you have looked into data already this is old news。For me it's a letdown because I was looking forward to maybe the most famous data researchers right now presenting his research。 So how did he estimate Trump could be elected when papers like Huffington Post said Silver was deluded and that Hillary had a 99% chance of being elected? This is what he is known for。 Describing how he does political polls with his team would be a great book。 Alas we got this basic data research overview。 But this book is from before he really blew up as it's from 2012, before Trump。 So maybe the time to write the book I wanted is now。On the other hand I was afraid the book would just be pro Democrat propaganda。 Nate Silver is a known gay Democrat and on Twitter you can see his ideology。 I was very positively surprised to not see much of this bias。 He did write about AIDS and a bit about politics, but I didn't see a single fully ideological sentence in the audiobook。 That's very impressive! He was biased in how he described Ronald Fisher and it was clearly an ideological bias, but it didn't feel over the top or that unfair overall。Overall the book is very hard to judge。 It's very impressive research into various topics and it's a book anyone outside the field could and should read。 It's a very strong book。 On the other hand I'm sure there is a much better book Nate Silver could write about what he actually does and how he gets it right more often than any pundit。 He is ideologically biased so we do see him fail at times, but he always admits to any failure and we continue on。 This is not how for example New York Times does it。 They make mistakes or lie and you won't always get an admittance of guilt。 Again, Silver is impressive in this way。 But he has become overly careful with his predictions to make fewer mistakes so he seldom makes surprising predictions。 This more layback style and his political convictions makes him a bit of a regular boring Democrat voter in media。 This is where pundits fit in。 They are always engaging。 With Silver not writing about his personal research, but instead a little bit about everything, it all feels impersonal。 On top of that it's a very hesitant book overall。The whole conclusion is that data is confusing and unpredictable。 No big colorful claims are made。If you need a book intro about data research into society this may be the best intro ever written。 Superforecasters is a great book too though, but is mainly about forecasters not about what they forecast or what they conclude。 But all these data books tend to just be a bit about nothing because this stuff is very unpredictable and it's hard to write a book about it without being seen as a bit of a believer in a weak soft science field。 So just because it's the best intro doesn't mean the field is so great that the best intro will be amazing。 It's fine。 。。。more

Christopher

I approached this book skeptically, having followed Nate Silver’s career since his time at the Times。 Still, I found it interesting and well-written and absolutely worth my time。

Victor M Anita Gtz。

I liked the part that refers to an possibility of a pandemic (taking in consideration that it was written before covid), and also the chapter that studied Mexico situation with H1N1。 It should be a warning of the disaster we have now :(

Bernard Tan

"The Signal and the Noise" by Nate Silver was Wall Street Journal's Nonfiction Book of the Year and a NYT best seller in 2012。 A new version was published in 2020 incorporating events that led up to Trumps's election。 Nate Silver is most famous for FiveThirtyEight, a website that focuses on opinion poll analysis, and predicts the outcome of American elections。Silver, a statistician and a rock star, makes the job of using statistics to predict outcomes exceptionally fun。 He started his career as "The Signal and the Noise" by Nate Silver was Wall Street Journal's Nonfiction Book of the Year and a NYT best seller in 2012。 A new version was published in 2020 incorporating events that led up to Trumps's election。 Nate Silver is most famous for FiveThirtyEight, a website that focuses on opinion poll analysis, and predicts the outcome of American elections。Silver, a statistician and a rock star, makes the job of using statistics to predict outcomes exceptionally fun。 He started his career as an associate in KPMG, studied baseball statistics during work hours, became a professional poker player before going bust, and then setting up FiveThirtyEight。 In this book, he covers human attempts to calculate and predict disparate outcomes - from earthquakes to baseball games, to the weather, to poker, chess, to the stock market, housing bubbles, elections, climate change and terrorism。 He introduces every topic simply and explains why it is possible to mistake noise for signal and miss the signal from the noise。 While the predictive capacity in certain areas has improved, man is still limited in his ability to definitively predict all outcomes。 Logic will state that the more complex the system, the more difficult the prediction。 But within that limitation, there are ways in which we can approach problems of uncertainty。 He introduces Bayesian probabilistic thinking, and the need to be open to multiple hypotheses and not be fooled by familiarity。 Highly recommended for those in the intelligence community, and for the average man who may want to appear smarter on a whole range of topics。 Articulating some of the points may make make you a better conversationalist and get you invited to more dinners。 One of the better books I have read this year。 。。。more

Everson Luis de Campos Moura

Some chapters are not interesting at allIf you know about and like baseball, poker, and american politics, maybe, you'll find the whole book very interesting。 However, if you, like me, don't know and don't like these subjects about half this book is difficult to read。 The other chapters are about more broad and interesting subjects: weather, earthquakes, stock markets etc。 Sometimes, it seems that the author keeps going around in circles, using the same theories and arguments again and again, ch Some chapters are not interesting at allIf you know about and like baseball, poker, and american politics, maybe, you'll find the whole book very interesting。 However, if you, like me, don't know and don't like these subjects about half this book is difficult to read。 The other chapters are about more broad and interesting subjects: weather, earthquakes, stock markets etc。 Sometimes, it seems that the author keeps going around in circles, using the same theories and arguments again and again, changing only the subject。 But I think it is worth reading。 At least, it is very useful to know that even an expert in forecasting is very concerned and aware about the limitations of forecasting and is trying to say to the world that it is better to understand that。 The author has the merit of being honest and clear about this。 。。。more

Liu Zhang

4。5 starsOnly because I’m familiar with some of the topics, when it’s first come out, it’s pretty good with the relevant development of the events。 In hindsight now, the promotion of Bayesian thinking is pretty good。

Andrii Tymchuk

Це вже далеко не перша прочитана мною книга, присвячена питанням застосування теорії ймовірності й статистики в реальному житті。 У такої літератури буває багато огріхів: надання завеликої значущості темі, обсмоктування тих самих тез упродовж усієї книжки, нестача конкретики。。。 У цієї книжки жодного з цих недоліків я знайти не зміг。Автор намагається охопити абсолютно всі сфери діяльності, де так чи інакше формуються певні прогнози за допомогою відповідних математичних методів。 І хоча від того кни Це вже далеко не перша прочитана мною книга, присвячена питанням застосування теорії ймовірності й статистики в реальному житті。 У такої літератури буває багато огріхів: надання завеликої значущості темі, обсмоктування тих самих тез упродовж усієї книжки, нестача конкретики。。。 У цієї книжки жодного з цих недоліків я знайти не зміг。Автор намагається охопити абсолютно всі сфери діяльності, де так чи інакше формуються певні прогнози за допомогою відповідних математичних методів。 І хоча від того книгу кидає в різні боки з розділу до розділу, в автора це прекрасно виходить。 Ще ніколи я так добре не запам'ятовував, про що йшлося в кожному окремому розділі: фінанси, політика, бейсбол, погода, землетруси, економіка, епідеміологія (актуально), баскетбол, шахи, покер, знову фінанси, клімат і національна безпека。 Виходить, що кожен розділ - це ніби початок зовсім нової книжки, тому інтерес до читання не спадає до самого кінця。 Незважаючи на великий обсяг книги (майже 500 сторінок основного тексту), у мене жодного разу не виникло бажання пошвидше з нею завершити。Також ця книга змусила мене всерйоз задуматися про те, щоб, окрім надання суб'єктивної оцінки на основі задоволення від прочитаного, розрізняти книжки за критерієм складності。 Усі хоч трошки віддалені від повсякденщини поняття автор прекрасно пояснює доступною мовою。 Тим не менш, під час читання я усвідомлював, що деякі з описаних концепцій чи думок я зрозумів би не так добре без якого-не-якого попереднього орієнтування в темі。 Тому, за складністю ця книга хоч і не є як повноцінна наукова праця, але вона стоїть значно далі за всяку беззмістовну мотиваційну літературу。Є момент, який трішки псував насолоду від читання, але це зовсім не провина автора。 Справа в。。。 перекладачеві, який з якогось дива усе, що напевно в оригіналі було "but" і "however", перекладав не "але" чи "проте", а виключно як "однак"。 І на одній сторінці могло вийти штук 10 оцих "однак"。 Можливо, хтось взагалі не зрозуміє претензії, але мені це здавалося геть яким неприродним。Усе ж, загальні враження від книги виключно позитивні。 Приємно усвідомлювати, що читаєш працю на одну з улюблених тематик від людини, яка справді глибоко розбирається в тому, про що пише。 。。。more

Bill Nielsen

Guy's smart, that much is true。 Loved the poker breakdown。 Loved learning about the pursuit to improve prediction models。 There's an honesty and humility in this book that stays with me。 Guy's smart, that much is true。 Loved the poker breakdown。 Loved learning about the pursuit to improve prediction models。 There's an honesty and humility in this book that stays with me。 。。。more

Kaelyn

3。5。 very informative and interesting points were discussed, but it was so dry that it took me 3x longer to read than it should have。

James

Interesting, pretty dry but a few good chapters。

Ana Mello

Very nice explanation of the difficulties of making predictions。 Specially liked how varied the examples were, showing that this isn't a failure of one specific area。 Very nice explanation of the difficulties of making predictions。 Specially liked how varied the examples were, showing that this isn't a failure of one specific area。 。。。more

James

Ironically, this book is mostly noise, with very little signal。 Author spends a very long time on digressions into the details of various examples than actually discussing how to make good predictions。 I was also hoping for some information theory content, but the terms "signal" and "noise" are only used in the nontechnical sense。Notes:t• Prediction is very important, and we are very bad at itt• Bad independence assumptions can lead to insane errors。 If I think dice rolls are independent, probab Ironically, this book is mostly noise, with very little signal。 Author spends a very long time on digressions into the details of various examples than actually discussing how to make good predictions。 I was also hoping for some information theory content, but the terms "signal" and "noise" are only used in the nontechnical sense。Notes:t• Prediction is very important, and we are very bad at itt• Bad independence assumptions can lead to insane errors。 If I think dice rolls are independent, probability of rolling five sixes is 1/6^5, but if they are not actually independent, it's just 1/6。 The greater the reliance on law of large numbers and the smaller the chances we're dealing with, the greater the error factors from incorrect independence assumptions。t• Political news formats systematically block signal and amplify noise。 If there's strong evidence for outcome X, it's unlikely that a news platform will parade on one expert after another reiterating the same case for X。 But if there's anyone who advocates ~X, they'll be brought on either for "getting both sides" or for unusualnesst• In chaotic weather systems, forecasts start off better than simple climate averages or one-day conditional probability models。 As time goes on, chaos takes over until the forecast no longer has an advantage (about a week out)。 But they don’t equalize there - forecasts end up worse than just guessing the average! Signal is gone, but noise keeps getting amplifiedt• Economic forecasts that have reputation attached do better than anonymous ones。 Better incentivest• In diseases without causal mechanism for diagnosis, rates of diagnosis scale with media coverage (per capita!)t• Stock market volumes have been doubling every four or five years。 Stocks used to be held for six years on average (1950s), which went down to six months (2000s)t• Weak efficient market hypothesis claims that predictions using only market history cannot beat market。 Semi-strong version claims that including public information still cannot beat market。 Strong version claims that even including private information cannot beat market。 Strong version is not empirically supported。t• Members of Congress, who often gain access to inside information about a company while they are lobbied and who also have some ability to influence the fate of companies through legislation, return a profit on theirtinvestments that beats market averages by 5 to 10 percent per year!t• Friction in the stock market does seem to prevent perfect efficiency。 Transaction costs, herding, everyone copying the same few strategies, interest rates on shorts and backing out of shorting deals, etctt○ Market appears to be largely inexploitable due to the amount of opt power dumped into it, but is still not efficient because of the structure of the market rules。t• A simulation in which investors were perfectly rational except for overconfidence in their predictions produced a lot of results that look like patterns in the modern stock market, lmaot• Only 19% of climate scientists said current models could make reliable 50-year predictions 。。。more

Nicholas Rush

Obviously on some topics this book is a little dated, but I found it incredibly interesting just to learn about the process of forecasting。 While it felt like a chore to get through the full audiobook, I think I would have loved "reading" a hard copy where I could have more easily jumped to the topics I was interested in。 I'd still recommend it for people who are into data and data science。 Obviously on some topics this book is a little dated, but I found it incredibly interesting just to learn about the process of forecasting。 While it felt like a chore to get through the full audiobook, I think I would have loved "reading" a hard copy where I could have more easily jumped to the topics I was interested in。 I'd still recommend it for people who are into data and data science。 。。。more

Rachael | Booklist Queen

Statistics Made InterestingWhy do most predictions, even those from experts, fail? From earthquakes to poker to political elections, Statistician Nate Silver uses interesting case studies to explain probability and uncertainty and demonstrate why predictions are often wrong。 Though the book is numbers-heavy and a little too long, Silver does a great job simplifying the information for the average reader。 

Pam

I really liked this book。 It talks about predictions and how useful statistics might or might not be in various cases。 I like math books and this one is well written and interesting。

Jelle

(3,5)Interesting read with useful insights / food for thought!The issue I had with the book, is that it concerns dense chapters which are really standalone/disconnected from each other which doesn't support the storyline。A more compacted/edited version, would make it a great read。The consecutive chapters focusing towards solutions (bayes theorem - chess - poker) are my personal highlights, which I marked as to reread。 However, I ended up skipping some of the other chapters or found those less in (3,5)Interesting read with useful insights / food for thought!The issue I had with the book, is that it concerns dense chapters which are really standalone/disconnected from each other which doesn't support the storyline。A more compacted/edited version, would make it a great read。The consecutive chapters focusing towards solutions (bayes theorem - chess - poker) are my personal highlights, which I marked as to reread。 However, I ended up skipping some of the other chapters or found those less infomational and/or entertaining。 。。。more

Zafer Sahinoglu

I come from an engineering background。 I have solved a large number of detection, estimation, forecasting and prediction problems throughout my career。 My expectation from the book was to provide a deeper and clear look into how signals that carry information can be identified and separated from noise to improve prediction performance。 I didn't expect it to be a textbook level reference。 The first quarter of the book was engaging and interesting。 However, the later chapters were far from introdu I come from an engineering background。 I have solved a large number of detection, estimation, forecasting and prediction problems throughout my career。 My expectation from the book was to provide a deeper and clear look into how signals that carry information can be identified and separated from noise to improve prediction performance。 I didn't expect it to be a textbook level reference。 The first quarter of the book was engaging and interesting。 However, the later chapters were far from introducing unique perspectives and insights to the reader。 The author in the end concludes by explaining benefits of applying Bayesian formula for better predictions, but only scratching the surface。 I expected much more from a 535 page book。 。。。more

Annie Fuller

Interesting topics, too long, distracting tone2。5 stars。 It was fine, but it needed better editing。 Early chapters are decent introduction to the subject of probabilistic thinking, but, in short order, Silver’s flippant and self-aggrandizing tone — full of unnecessary quips and anecdotes — becomes grating。Certain chapters on predictions involving the financial crisis, weather and earthquakes were more engaging。 When discussing Silver’s pet topics (baseball, poker, politics, economics), it’s hard Interesting topics, too long, distracting tone2。5 stars。 It was fine, but it needed better editing。 Early chapters are decent introduction to the subject of probabilistic thinking, but, in short order, Silver’s flippant and self-aggrandizing tone — full of unnecessary quips and anecdotes — becomes grating。Certain chapters on predictions involving the financial crisis, weather and earthquakes were more engaging。 When discussing Silver’s pet topics (baseball, poker, politics, economics), it’s hard to get with the gist of the chapter without being distracted at phrases like: “While everyone else at the party was chasing down Susan Sarandon, we parked ourselves at the bar and chatted for a while。”“‘No consensus was found。 Therefore I suspend this agenda item,’ said a French-sounding woman, mustering her best English。”“Emanuel’s office at MIT, designated as room 54-1814, is something of a challenge to find (I was assisted by an exceptional janitor who may as well have been the inspiration for Good Will Hunting)。”Those sidebars alone may give you an idea if the book is for you。Finally, I did like Silver’s pro-Bayesian argument (against Fisher’s frequentist approach)。 Some good content in this book, if you want to take the time to sift through it。 。。。more

Sean

Bayesian inference / Bayes theorem ftw - enjoyed this read a lot especially the part about embracing the unknowns in this world。 Topics covered were also broad and insightful。

Trevor Pownell

Nate Silver walks through the triumphs and traps of predictions through real world examples (baseball, weather, political elections, etc。)。 This is essentially a storyteller's version of a statistics class。 I walk away with healthy skepticism in interpreting what I read/see day-to-day (albeit more from an anecdotal level than a technical level) and an optimism for developments to come in the space。 Good book to run down curiosity, not a great book if you're looking to be on edge of your seat。 “W Nate Silver walks through the triumphs and traps of predictions through real world examples (baseball, weather, political elections, etc。)。 This is essentially a storyteller's version of a statistics class。 I walk away with healthy skepticism in interpreting what I read/see day-to-day (albeit more from an anecdotal level than a technical level) and an optimism for developments to come in the space。 Good book to run down curiosity, not a great book if you're looking to be on edge of your seat。 “We need to stop, and admit it: we have a prediction problem。 We love to predict things—and we aren’t very good at it。” - Nate Silver 。。。more

Cari

A rather boring book。 Interesting information that would have been more engaging to read in a storytelling format like Malcolm Gladwell (ironically, the author slams Gladwell in one of the chapters)。