The Art of Uncertainty: How to Navigate Chance, Ignorance, Risk and Luck

by David Spiegelhalter

From the UK’s ‘statistical national treasure’, a clever and data-driven guide to how we can live with risk and uncertainty

Life is uncertain. We are all the result of an unforeseen and unforeseeable sequence of small occurrences. But what underlies this fragile chain of events? Is it random or just complex? And what role does luck play in our lives?

David Spiegelhalter has spent his career crunching data in order to help understand uncertainty and assess the chances of what might happen. In The Art of Uncertainty, he gives readers a window onto how we can all do this better.

Uncertainty, he argues, is a relationship between the observer and an object in the outside world. He shows us how we can express it numerically, and then update our beliefs about the future in the face of constantly changing experience. In crystal-clear prose, he takes us through the principles of probability, a field that informs everything from annuities to pandemics and climate change, while also examining the limitations of statistical modelling and arguing we need to have the humility to admit our ignorance.

Drawing on a wide range of real-world examples, this is an essential guide to navigating uncertainty in a world that makes it inevitable.

Genres: Nonfiction, Science, Psychology, Mathematics, Business, Economics, Finance

512 pages, Hardcover

First published September 19, 2024

About the author

Sir David Spiegelhalter has been Winton Professor of the Public Understanding of Risk at the University of Cambridge since October 2007. His background is in medical statistics, with an emphasis on Bayesian methods: his MRC team developed the BUGS software which has become the primary platform for applying modern Bayesian analysis using simulation technology. He has worked on clinical trials and drug safety and consulted and taught in a number of pharmaceutical companies, and also collaborates on developing methods for health technology assessment applicable to organisations such as NICE. His interest in performance monitoring led to his being asked to lead the statistical team in the Bristol Royal Infirmary Inquiry, and he also gave evidence to the Shipman Inquiry.

Reviews

[Richard Marney · Rating 5 out of 5]

I read this book through twice. The first at a quick coffee shop pace and the second delving more deeply into the subject matter.

Much of the material has been covered elsewhere in the vast literature on the general topic area, but the author distinguishes himself in the quality of the organization and writing. The book makes it to the reference library!!!

[Rory · Rating 3 out of 5]

I am very interested in the topic, but I like clarity of communication: the author leans towards words that are not in common usage, and that somewhat foggy style of communication takes away from the accessibility of the text.

The chapters dealing with uncertainty, and with guidance for the communication of uncertainty, were the most impactful; there were some excellent takeaways that straddled a line between statistical analysis and crisis management, and the writing style was far less dense than in the preceding chapters. This aspect of the book was more resonant than the sections that came before, which were more mathematically oriented, and not very well presented.

[katie meddins (maresh) · Rating 4 out of 5]

4.5
should be essential reading

[Nacho · Rating 3 out of 5]

Solid read , a great deep dive into uncertainty in a digestible way. IMO the author was aiming to structure his chapters like a Malcom gladwell book and I would say he got 65% of the way there . The examples used to build up concepts and unpack probabilities/uncertainty were good but I felt they never expanded enough . The author engaged with the example enough to intrigue but never enough to satisfy . However there are fantastic chapters that I would pluck out

[Kate · Rating 4 out of 5]

I’ve always hated statistics, especially at uni, but I love this author so I struggled through just for him

[Ali · Rating 4 out of 5]

I like evidence, and I enjoy learning, and as such, I like turning uncertainty into certainty - or at least working out how to understand - so this book was a real joy for me. Spiegelhalter starts with a basic understanding of probability, and moves on to look at various practical applications from seeking to understand what is unknown, through to prediction of events small and not so small. The book refers at times to some of the most pressing issues around prediction, from climate change to probable future pandemics, but the star here is the process of understanding and making this chaotic world just a tiny bit more predictable. There is some mathmatical concepts, but it is formula-lite if not formula-free.

[Gijs Limonard · Rating 3 out of 5]

There is absolutely nothing wrong with this work on probability, only that it is pretty generic and boring. For the interested reader for the first time dipping his/her toe into the literature on probability theory this suffices as a decent primer; for all others please refer to these excellent works: all the books by Taleb Nassim Nicholas and Bernoulli's Fallacy: Statistical Illogic and the Crisis of Modern Science.

[Karlis Skulte · Rating 3 out of 5]

There were a few interesting topics and discussions such as reframing how general descriptions of likelihood vs probability can be easily misunderstood without supporting data and how confidence weighted decision making can shine a light on degree of certainty. However, fairly long sections of the book read as a textbook with detailed explanations of statistics and probably methodology and calculations and were a bit of a bear to push through. There are warnings about this in the beginning of the book, so it shouldn’t come as a surprise.

[Robin Perkins · Rating 3 out of 5]

I received this book as part of a Goodreads giveaway.


This is a text full of information. However, it can be a difficult read as it is presented very straightforward and mechanical. The examples are solid, but are presented mechanically. It makes the book very dry to read and can get long-winded at times. When picking this text up know it reads more like a textbook than a casual read book.

[Marie Clarke · Rating 4 out of 5]

I think this would be better read rather than listened to. Some fabulous facts and interesting stand points. Heavy on the statistics as should be expected, all very well explained but will need another listen.

[Ashley Denktas · Rating 3 out of 5]

I enjoyed this book, but it was a bit hard to get through at some parts. Not because it wasn't engaging, but because I struggled to understand the mathematical analysis. I did try on scratch paper to work out some problems to understand them which was a humbling experience that did help strengthen my understanding a bit more, but also made me realize two things: I forgot how to do algebra and that probability requires really fully understanding how you are presenting a situation (and I currently struggle to do that in a mathematical sense). Part of me wishes that some of the analysis showed how the calculations were done, but I do realize this isn't an introductory book.

I picked this book up because I wanted to get more acquainted and comfortable with uncertainty. I did think this was a self-help book, so when the book opened with it's focus on probability it was a nice twist for me since it framed this in a new light. Spiegelhalter defines uncertainty as not a property of the world, but a feeling about our relationship to it (which changes as we get more "data," thus is affected by the subjective perspective and knowledge of the observer). Uncertainty is part of a long series of circumstances and decisions that have allowed us to exist/ be born and live life to day. Not understanding everything or knowing what comes next is part of life. However, uncertainty can be a source of anxiety or a feeling of opportunity. As someone more familiar with the former, this book was helpful in showcasing that uncertainty thinking is dominated by "what could happen" rather than "will it happen?". In learning more about how we can measure uncertainty, it helped reframe my thoughts on it as well as provide frameworks for questions we should all be asking ourselves when reading data or consuming media/studies reference probability and risk. My TLDR based on the notes I took below:

1. Numerical probability can be misunderstood if we don't all have the same definitions for words that measure probability: "likely" "maybe" "probable". For example, John F. Kennedy had approved the bay of pigs invasion because the report said that it had "a fair chance" of succeeding. In actuality "fair chance" meant 30%, which in laymen terms would be not good.
2. Probabilities are not right or wrong but give a range of options that could happen. The cited example showed that Trump was predicted by one commentator to have a 29% probability of winning in 2016 (less than 1 in 3). Based on the set of judgements about popular opinion we had on the time it was showcasing the specific set of outcomes that could happen.
3. Coincidence - A surprising concurrence of events, perceived as meaningfully related with no apparent causal connection. However, if you want some party tricks (thank you):
- If you're in a group of 23 people, there's a 50% chance someone has the same birthday. (95% in 45).
- If you are in a group of 20 people, there is a 87% chance someone has two matching last digits of a phone number or license plate.
4. We need to constantly question our assumptions and have the humility to acknowledge that the whole basis of our thinking may be incorrect.
5. There is no force that will encourage something to happen in spaced out intervals of time, so the most likely time for the next occurrence is immediately. Randomness is often "clumpy." If there's a big plane crash, maybe I'll wait a little bit to get on the next plane.
6. We should be wary of automatically trusting people presenting information (and in life).
7. All models are wrong, but some are useful. They incorporate numerous assumptions that can never be fully false or cannot be confirmed. Can't build on one model, we need multiple and different perspectives. "Models are fictions, just metaphors for reality, and sometimes we should just admit we don't fully understand what is going on."
8. In communication you should articulate, what you know, what you don't know, how you plan to find out more, current advice, and that advice might change based on more observation/ judgements.
9. Trying to persuade audiences, balanced communication was more trustworthy than persuasive.

My other personal takeaway from this book was to think in probability trees. It is easy to get focused on one specific outcome when there are actually infinite ways a situation and life could play out. Life is not just if, then, but a series of if, then, but, and, therefore that branch in endless directions. I have forgotten that, and truly appreciate this book for reminding me. In closing, "We cannot avoid uncertainty. So we need to embrace it, be humbled by it, and even try to enjoy it."

[Chad Manske · Rating 4 out of 5]

David Spiegelhalter’s “The Art of Uncertainty: How to Navigate Chance, Ignorance, Risk and Luck” offers a masterclass in understanding and embracing the unpredictable nature of our world. Spiegelhalter, a renowned statistician, doesn’t simply teach probability—he reframes uncertainty as a deeply personal relationship between ourselves and the unknown, challenging the reader to see uncertainty not as a flaw in our knowledge, but as an inevitable feature of existence.
**Uncertainty as Personal**
Spiegelhalter argues that uncertainty isn’t an objective property of the world, but a reflection of our own knowledge and perspective. What’s uncertain to one person may be obvious to another, depending on their background and information.
**Quantifying the Unknown**
The book urges readers to move beyond vague terms like “likely” or “possible.” Spiegelhalter demonstrates how expressing uncertainty numerically—using probabilities—can clarify thinking and communication, especially in fields like medicine, climate science, and public policy.
**Probability, Risk, and Luck**
Through lively prose and real-world examples, Spiegelhalter explores the principles of probability, the difference between hazard and risk, and the role of luck in shaping outcomes. He illustrates how misinterpretations of probability have led to historical blunders, from the Bay of Pigs to maritime disasters.
**Decision-Making and Emotional Responses**
The book delves into the psychological side of uncertainty, showing how our emotions and biases shape decisions. Spiegelhalter offers strategies for making better choices under uncertainty, including updating beliefs as new evidence emerges—a nod to Bayesian reasoning.
**Communicating Uncertainty**
Spiegelhalter emphasizes transparency and honesty, advocating for clear language and visual aids to help others grasp complex risks and probabilities.
This isn’t a breezy self-help manual—it’s a rigorous, yet accessible, exploration for anyone interested in statistics, science, or simply making smarter decisions in a complex world. Teachers, business leaders, and curious readers alike will find Spiegelhalter’s wealth of relatable examples and practical wisdom invaluable. “The Art of Uncertainty” ultimately teaches us to be humble in the face of the unknown—and to find empowerment, not fear, in life’s unpredictability.

[James Smith · Rating 4 out of 5]

As the baseline the book is very well balanced on being enjoyable and useful. The core idea communicated is in understanding what kind of statistics and data analysis we see in the world, and how it's communicated. You gain perspective on how to interpret claims of all sorts and the book helps develop more well rounded intuition from a statistical perspective on what you see and what's missing. It's not super technical and at certain parts the statistics itself are slightly glazed over. For a very good introduction to statistics and data analysis on an accessible, yet slightly more technical level I'd recommend Spiegelhalter's other book, "The Art of Statistics: Learning From Data".

There are tons of examples and stories that are entertaining and serve to illustrate a point, creating a strong balance between intrigue, information and pleasure. Though to those with a background in (for example) statistics, data science or academics many of the topics are rather basic, I do think it's a very worthwhile read. Even topics that were previously familiar weren't tedious to read through, and I found the additional perspective and discussion offered in the book to be very valuable and interesting. All in all a very good book, written very well with useful and important ideas weaved throughout.

[Robert Muller · Rating 5 out of 5]

A mid-level introduction to the application of probability. This is NOT statistics, and that's a plus--people need to understand what probability is and is not and how you can use it to understand what you know and don't know. There's just enough math here to get you into the basics, and that leads you directly into Bayesian thinking without delving too far into the more arcane aspects of things like probability distributions. Speigelhalter's excellent and clear writing style is way beyond the usual book on these subjects and makes everything very clear, especially with respect to what isn't clear at all. That's what uncertainty is all about.

[Marie Edlund · Rating 4 out of 5]

Detta är en bok som tar ett större grepp om statistik än bara beräknings teknik. Spännande och viktiga tankar att ta med sig.

[Marnix Verplancke · Rating 4 out of 5]

Wij mensen zijn de speelbal van het toeval en de onzekerheid. Als je moeder en je vader elkaar niet hadden ontmoet, was je er nooit geweest. En dat je hier bent geboren en niet in Gaza heb je ook niet zelf gekozen, net zomin als je genetische aanleg voor een of andere kwaal. En dat is nog maar het begin, want een mensenleven bestaat voor een groot deel uit keuzes maken. Wat je gaat studeren, welke job je aanvaardt en of je nu wel of niet in zee wil met die man of vrouw waar het mee klikt, waarna er misschien kinderen komen en alles van voor af aan herbegint. Hoe gaan we om met die onzekerheid en op welke basis maken we de beste keuzes? Statisticus David Spiegelhalter schreef er een verhelderend boek over, The Art of Uncertainty, How to Navigate Chance, Ignorance, Risk and Luck.

[Alok Bharadwaj · Rating 5 out of 5]

Uncertainty has certainly marked the first half of 2020's. Starting with the Pandemic, wars, and the changing technological landscape - this decade has made sure that humans have to live through some of the most uncertain years of their lives. Against this backdrop, a renowned statistician comes with a timely book teaching us how to "think" about uncertainty.

David Spiegelhalter makes a convincing case that uncertainty is a "relationship", and not an objective feature of the world. This requires some thinking through. What exactly does it mean? It means, for one, every one of us could have different degrees of uncertainty regarding the same set of data. Why? Because we all live through different lives, and have consequently developed different "inner models" of how the world works. We literally see the world differently.

The fact that everyone of us have different biases, and perspectives need not alarm us. In fact, it might very well be humanities greatest strength. As David explains, the best decisions are made when we combine predictions from different independent models. In that spirit, we should all welcome uncertainties and not try to hide it. We should make space for people to voice out differences in opinion, so that we atleast understand what the range of plausible models are out there.

The book does not aim to be a self-help book. However, given the nature of the topic, it cannot help but delve into some personal advice. Given that the world we live in is increasingly complex, it is almost guaranteed that we have to confront what David calls "Deep Uncertainties". These are the class of uncertainties for which, it's not just a matter of not having empirical data but rather we don't even have a proper model to establish some baseline priors. In various other works they are called "Black Swan" events, those which are far outside the norm.

The personal narrative that we tell ourselves provides us with the direction with which we need to act in such circumstances. When numbers fail us, stories show the light. It is therefore all the more important that we are able to reflect on what kind of stories we tell ourselves, since that defines how we act in the face of deep uncertainty.

[fish_fin · Rating 5 out of 5]

A fun read, lots of interesting anecdotes on how statistics is used and how it should be used.

[Mikala · Rating 3 out of 5]

I switched my major in college from biology to chemistry specifically to avoid taking additional statistics courses. I excelled in all upper division math classes, but statistics was too boring to survive. Of all the college courses, it is the most applicable to life. Like learning to balance a budget or get signatures from 6 professors when 4 of them are on sabbatical so you can graduate on time, having an innate grasp on statistics would set you on a path of a lifetime of success - if somewhat boring success.
All this is to say, I found this book the same as those college courses. Tedious to the point of absurdity. Yes, it's true I don't understand statistic. Yes, you can say 1 out of 10 or 10% and my brain knows it's the same thing but the emotions are different if we're talking about the lottery odds or cancer risks. The book tries hard to make you understand that these are the same stats with repetitive and occasional dull stories about taxes. Imagine behavioral economics before the "behavioral" part - before Freakonomics. It's just a lot of statistical analysis geeks hanging around in a convention hall talking spreadsheets and error bars.
This is a good book for someone that already is into statistics or someone who might want a career in actuarial sciences. For the "rest of us," I'll wait for a decent podcast about it and keep messing up statistics every time I hear the news.

[Alex W · Rating 2 out of 5]

I had high hopes for this book, but ultimately felt disappointed at the end. I felt excited at first as the chapter overview showed a number of interesting topics that I felt particularly curious to learn more about or refresh. The book also opened strongly with some interesting anecdotes, fun exercises and engaging revision of some core probability concepts. However from the middle I started to lose interest. Much of the latter part of the book is dedicated to hammering home the same points (that it’s difficult to model uncertainty and that it’s difficult to communicate about it). The repeated use of the same examples (e.g. COVID, climate change) didn’t help. A more diverse range of examples would have made for a more engaging read. Ultimately I think that this is a classic example of a book that should have been 50% shorter.

[Robin Barnwell · Rating 3 out of 5]

Difficult review this one.

The core concepts in the book are dynamite. It’s just such a pity the explanations are so poor.

It’s like the author wrote the book with himself as the customer. There are “in jokes” that you have to google to find out the story. The explanations are for people who already know the materials.

The example used for Bayes Theorem is very misleading. It’s only later in the Chapter that the author says the person actually knows the expected contents of the two bags. I thought he was trying to be ironic and give some posterior information. But it’s just a poor explanation.

I’m sure the author is a great statistician but I don’t think he is good at getting the point across 🙁

[Nicola Waters · Rating 2 out of 5]

I did a maths degree, and stats and probability were always one of my favourite parts. But professionally I’ve mostly had no cause to study further because maths is tangential to my job at best. You’d think therefore I might be the ideal reader for such a book- and at first seemed very promising, nice refresher on the stuff I always liked around calculating probability. But I couldn’t finish it- more and more detail that felt like it belonged more in a textbook. Might be a failing on my part, but my suspicion is, if a maths grad who always enjoyed this subject are struggled with it, then a complete layman would be lost.

[Luke Wiest · Rating 2 out of 5]

I read the first seven chapters, skimmed the next three, and then put it away. My biggest takeaway from this book is that you need to look into the statistics of any article or study you read before you start quoting it's findings. I've taken a couple of statistics courses so the math wasn't new to me. The scenarios were interesting but the book as a whole wasn't compelling enough to keep me engaged.

[Lupin · Rating 1 out of 5]

Gave this book a low score more because I learnt so little from it, rather than it was 'bad'.

One thing I would say against it, is that it makes some effort to explain things if they involve high-school level maths, but if it's anything higher, it doesn't explain it at all, which is what I'd wanted from the book.

[Feng Ouyang · Rating 4 out of 5]

"The Art of Uncertainty" by Sir David Spiegelhalter offers both an introduction to statistical thinking and a public communication effort to clarify how probability and uncertainty shape decisions in everyday life and public policy. Spiegelhalter, a distinguished academic in statistics and an official of the UK Statistics Authority, brings expertise and authority to the subject.

The book begins by emphasizing that uncertainty is unavoidable in human life. Most people, Spiegelhalter notes, tend to respond to uncertainty with misguided intuitions and emotions that cloud rational decision-making. To address this, the book explores how uncertainty can be quantified. It introduces probability, explains different methods for estimating probabilities, and examines the uncertainties that arise during estimation itself.

From there, Spiegelhalter tackles especially important and challenging scenarios, such as assessing causal relationships within data, addressing rare but high-impact events, and predicting the future in the face of unknowns.

He also considers foundational debates, such as whether probability represents an objective reality or simply a reflection of human ignorance, and clarifies distinctions like the difference between risk and hazard. Spiegelhalter discusses approaches that blend subjective and objective estimation of what he calls "atomic probabilities." Building on these foundations, probability estimates can then be extended and refined through well-established mathematical methods.

The book succeeds in addressing a pressing need in modern society: understanding probability-based decision-making for both personal choices and policy-level debates. Real-life examples are used effectively to illustrate abstract concepts. However, one notable limitation is the lack of a clearly defined audience. At times, Spiegelhalter delves into nuanced discussions suited for experts or advanced learners, while other sections appear aimed at complete beginners. Readers may need to accept that only certain portions will feel directly useful to them.

The use of equations and detailed numerical examples adds technical depth, but they are not essential for communicating the main ideas. These features make the audiobook format less effective. In addition, Spiegelhalter frequently draws on his personal experiences, particularly in relation to his work on UK government policy. While these anecdotes help illustrate underlying principles and highlight the real-world value of statistical thinking, they create the impression that the book is partly serving as advocacy rather than pure popular science.

Overall, "The Art of Uncertainty" fulfills an important role by deepening public understanding of uncertainty, probability, and risk. Its content is highly relevant for managing personal decisions and engaging in informed public discourse. Although the delivery could be more consistently tailored and streamlined, Spiegelhalter’s expertise and enthusiasm make this an enlightening and valuable resource.

[Brian Clegg · Rating 5 out of 5]

There's something odd about this chunky book on probability - the title doesn't mention the P word at all. This is because David Spiegelhalter (Professor Sir David to give him his full title) has what some mathematicians would consider a controversial viewpoint. As he puts it 'all probabilities are judgements expressing personal uncertainty.' He strongly (and convincingly) argues that while the mathematical approach to probability is about concrete, factual values, outside of the 'natural' probabilities behind quantum effects, almost all real world probability is a subjective experience, better described by more subjective terms like uncertainty, chance and luck.

A classic way to distinguish between those taking the frequentist approach to probability and the Bayesian approach is their attitude to what the probability is of a fair coin coming up heads or tails after the coin has been tossed but before we have looked at it. The frequentist would say it's definitely heads or tails, but we can't say which. The Bayesian would say it's still 50:50 because we don't have any information yet. Spiegelhalter puts himself firmly into the Bayesian camp. However, even the most rabid frequentist could not find issue with Spiegelhalter's careful and detailed introduction to the nature of probability and how we use it.

There are plenty of real world examples here, from Covid-19 risks to picking socks at random from a drawer. Spiegelhalter provides us with a range of stories to back these examples up, making large parts of the content highly readable. If I have a criticism, I think the book is too long and could have had a tighter structure. I felt myself drifting away from interest and skipping through a few pages (it is over 400 pages long) occasionally - but always came back into focus as a new topic was covered.

As was the case with its earlier companion, The Art of Statistics, this is not going to turn you into an expert. Although there is some gentle mathematics, there is nothing more complicated than getting your head around conditional probability representations - but there is no doubt that reading the book will give you a better idea of what probability is, how it's used and abused, and why we can be more precise about some predictions than others. You will have to work a little to absorb what's in here - but it's worth the effort.

I think this pair of books should become classics, very much in the tradition of the Pelican imprint, which always been intended to inform non-experts without patronising. If you've ever heard Spiegelhalter speak, everything is put across in a warm, favourite uncle fashion - this is the case with the best parts of his writing too. It's a voice of reason in an area that can sometimes seem counter-intuitive, and it is very welcome.

[Rory Fox · Rating 5 out of 5]

Although the focus is firmly upon the idea of uncertainty, the book ranges wider over linked concepts, such as luck, coincidence, probability, likeliness.

At the heart of the book is a definition. ‘Uncertainty is a relationship between someone… and the outside world, so it depends on the subjective perspective and knowledge of the observer.’ (Preface). That definition means that the book recognises, but largely ignores issues to do with uncertainty in reality, such as events that have not yet occurred (aleatory uncertainty), as the focus is upon our (subjective) knowledge or ignorance of reality (epistemic uncertainty).

A question which runs through the book, and crops up to varying extents in different chapters is whether uncertainty is an issue in cognition (thinking), or in emotion (feeling) or is it a behavioural matter, simply affecting what we do? Or perhaps all those elements feature to different extents in different contexts?

There is a lot of theory in the book, especially concerning probability and statistics. But there are also little stories and anecdotes to illustrate the issues. A well known example includes the Bay of Pigs invasion of Cuba in 1961. Kennedy authorised it because he was told that there was a ‘fair chance’ of success. He understood ‘fair chance as meaning more than 50%. But the analyst who wrote those words, really meant that the probably was something like 20%. So, decision making was completely derailed by a confusion in language, which masked deeper confusions about issues of how to assess risk and report the differing factors of probably and confidence in the data.

The author also appealed to well-known parables to illustrate the issues. For example, the parable of the hedgehogs and the foxes is a story about a hedgehog who has a single plan and a fox who is full of ideas. When disaster strikes the hedgehog can put its single plan straight into action while the fox is so spoiled for choice, that it runs round in circles, to its own detriment.

What makes that parable useful, is that it also describes personality attitudes and strategies of risk taking and forecasting which can be measured and reported back to individuals, to help them acquire better self-understanding and thus improve their management of uncertainty.

Textually, around 1/3 of the book consists of footnotes and follow-up materials. So the presentation is well supported with information for readers who want to pursue matters further.

Overall, this is not an ‘easy’ read. But it is presented clearly and if readers are prepared to give it the time and attention it needs then there is a lot to be learned about the concepts of certainty and uncertainty and about the issues which impact upon political and economic decision making.

[Ben]

My Dad got me this book after I got a job as an actuary and I worried that it would contain no information whatsoever that I didn't already know. However I ended up actually learning some things, which is a relief. Mostly soft things, like the fact that all probability is an expression of a relationship between an observer and the world, an expression of uncertainty given your information, rather than anything real in the world, or the fact that when a statistician gives a p-value to an observation, that value assumes the correctness of the model, which is itself uncertain, and this can be hard to account for. It's not that I didn't think these things before, but it's nice to have insights like these stated precisely and then elaborated on by a person with a lifetime's expertise in the subject. I also gained some harrowing examples to support my existing opinions on how poor an average (or even a supposedly smart) person's understanding of maths often is. E.g. a supposed "expert" arguing in court that, because the probability of a given baby dying of sudden infant death syndrome (SIDS) was 1/8543, the probability of it happening twice in one family with two children is (1/8543)^2, which is roughly 1 in 73 million, and therefore this is the probability that a mother both of whose children supposedly died of SIDS didn't instead murder her children. This not only assumes that the events are independent, which they obviously wouldn't be, but more importantly it ignores how unlikely a given mother is to murder her children and ignores any other possible causes of the deaths. It literally assumes that, given all families with two children, both of whom die in infancy with no apparent cause, 1 in 73 million have both children dying of SIDS, and all the rest have both children murdered by their mother. Obviously ridiculous, but this particular mother (Sally Clark) was actually sentenced and served more than three years in prison. Upon being released she drank herself to death, as I'm sure I would have. Meanwhile the idiot who supplied this argument in court is still alive and has been knighted!

In the last 3 non-fiction books I've read I've noticed typos, which makes me want to start keeping track. I found 4 typos in this book. On page 145 the "teams" in "those teams at the top of the table" should instead be "leagues". On page 273 the expression (RR-1)/R should instead be (RR-1)/RR. On page 322 there is a table with one entry being "Makes born in 2045" which should be "Males born in 2045". On page 338 there is a graph where the x axis goes 0, 5, 10, 15, 20, 20 which should instead be 0, 5, 10, 15, 20, 25.

[G Flores · Rating 4 out of 5]

Spiegelhalter does his best to manage the unwieldy nature of the topic he has chosen for this book which is to say that he neither fails nor does he fully succeed. The result is a delightful book on the mathematics of probability, chance and statistical analytics that has a general upward trend in difficulty with some moments of wild vacillation in terms of accessibility.

While my personal ability to absorb information became seriously strained about 2/3 of the way through the book, there are some excellent insights to be gleaned, some important reminders about perceived "fairness" and the way we interact with the world around us, and several opportunities to learn about the way large numbers, probability and statistics work in a practical sense and how those are rarely intuitive and with some regularity seem counterintuitive.

Through all the heady mathematical analysis (while the author endeavors to make the book accessible to the layman, some amount of maths are unavoidable given the subject), Spiegelhalter manages to entertain as he teaches, using relevant scenarios, the nearly perfect amount of "fun facts" about historical figures and trends and stories involving his personal narrative. This light touch of levity goes a long way towards making the medicine go down which is saying a lot. Highly recommended for anybody interested in the subject and doesn't mind putting in a little of the mental work required.

[Malin Friess · Rating 2 out of 5]

The Art of Uncertainty ended up being a 2-star read for me. I went in hoping for a more accessible, big-picture discussion of risk and uncertainty, but the book gets deep into the weeds of probability and statistics, with formulas that made it feel dry and technical rather than engaging.

It does raise interesting questions: what really causes climate change, how likely it is that AI could threaten human life, whether medication benefits are worth the side effects, and how we should think about low‑probability but high‑impact events. The most useful part for me was the communication framework the author suggests when talking with people about something important: 1) what we know, 2) what we don’t know, 3) what we are doing to find out, 4) what people can do in the meantime, and 5) that our plans may need to change as we learn more.

The book also points out that we often misjudge risk, greatly overestimating dangers like scuba diving or coal mining while underestimating everyday risks; for example, driving a car 25,000 miles is described as about 20 times more dangerous than those activities.

Just two stars.