Skip to main content

Everything is Predictable - Tom Chivers *****

There's a stereotype of computer users: Mac users are creative and cool, while PC users are businesslike and unimaginative. Less well-known is that the world of statistics has an equivalent division. Bayesians are the Mac users of the stats world, where frequentists are the PC people. This book sets out to show why Bayesians are not just cool, but also mostly right.

Tom Chivers does an excellent job of giving us some historical background, then dives into two key aspects of the use of statistics. These are in science, where the standard approach is frequentist and Bayes only creeps into a few specific applications, such as the accuracy of medical tests, and in decision theory where Bayes is dominant.

If this all sounds very dry and unexciting, it's quite the reverse. I admit, I love probability and statistics, and I am something of a closet Bayesian*), but Chivers' light and entertaining style means that what could have been the mathematical equivalent of debating angels on the heads of a pin becomes both enthralling and relatively easy to understand. You may have to re-read a few sentences, because there is a bit of a head-scrambling concept at the heart of the debate - but it's well worth it.

A trivial way of representing the difference between Bayesian and frequentist statistics is how you respond to the question 'What's the chance of the result being a head?' when looking at a coin that has already been tossed, but that you haven't seen. Bayesian statistics takes into account what you already know. As you don't know what the outcome is, you can only realistically say it's 50:50, or 0.5 in the usual mathematical representation. By contrast, frequentist statistics says that as the coin has been tossed, it is definitely heads or tails with probability 1... but we can't say which. This seems perhaps unimportant - but the distinction becomes crucial when considering the outcome of scientific studies.

Thankfully, Chivers goes into in significant detail the problem that arises because in most scientific use of (frequentist) probability, what the results show is not what we actually want to know. In the social sciences, a marker for a result being 'significant' is a p-value of less that 0.05. This means that if the null hypothesis is true (the effect you are considering doesn't exist), then you would only get this result 1 in 20 times or less. But what we really want to know is not the chance of this result if the hypothesis is true, but rather what's the chance that the hypothesis is true - and that's a totally different thing.

Chivers gives the example of 'it's the difference between "There's only a 1 in 8 billion chance that a given human is the Pope" and "There's only a 1 in 8 billion chance that the Pope is human"'. At risk of repetition because it's so important, frequentist statistics, as used by most scientists, tells us the chance of getting the result if the hypothesis is true; Bayesian statistics works out what the chance is of the hypothesis being true - which most would say is what we really want to know. In fact, as Chivers points out, most scientists don't even know that they aren't showing the chance of the hypothesis being true - and this even true of many textbooks for scientists on how to use statistics.

At this point, most normal humans would say 'Why don't those stupid scientists use Bayes?' But there is a catch. To be able to find how likely the hypothesis is, we need a 'prior probability' - a starting point which Bayes' theorem then modifies using the evidence we have. This feels subjective, and for the first attempt at a study it certainly can be. But, as Chivers points out, in many scientific studies there is existing evidence to provide that starting point - the frequentist approach throws away this useful knowledge.

Is the book perfect? Well, I suspect as a goodish Bayesian I can never say something is perfect. I found it hard to engage with an overlong chapter called 'the Bayesian brain' that is not about using Bayes, but rather trying to show that our brains take this approach, which all felt a bit too hypothetical for me. And Chivers repeats the oft-seen attack on poor old Fred Hoyle, taking his comment about evolution and 'a whirlwind passing through a junkyard creating a Boeing 747' in a way that oversimplifies Hoyle's original meaning. But these are trivial concerns.

I can't remember when I last enjoyed a popular maths book so much. It's a delight.

* Not entirely a closet Bayesian - my book Dice World includes an experiment using Bayesian statistics to work out what kind of dog I have, given a mug that's on my desk.

Hardback:   
Kindle:  
Using these links earns us commission at no cost to you
Review by Brian Clegg - See all Brian's online articles or subscribe to a weekly email free here
Labels:

Comments

Post a Comment

Popular posts from this blog

Luna: Moon Rising (SF) - Ian McDonald ****

I'm not the natural audience for this book. Game of Thrones l eaves me cold - and it's hard not to feel the influence of GoT (and a whole lot of Dune )   underneath a veneer of science fiction and the trappings of a South American drug cartel in the cod-medieval family power battles and chivalric details. There are even dragons (of a sort). I'd be really sad if the future did involve this sort of throwback feudalism. However, remarkably, despite this I found Luna: Moon Rising kept me engaged. The fact is that Ian McDonald can put together a good plot with intricate machinations, which is enough to carry the reader through what can be a bewildering collection of characters. The two page scene-setter saying who did what to whom at the start was useful, but I could have done with family trees for the main family as I was constantly forgetting who was who - especially easy as McDonald endows many families with characters with the same first initial (e.g. Ariel and Al...
Post a Comment
Read more

Adventures of a Computational Explorer - Stephen Wolfram ***

Stephen Wolfram, the man behind the scientist's mathematical tool of choice, Mathematica, plus a whole host of other software products, including the uncanny Wolfram Alpha knowledge engine, is undoubtedly a genius of the first order. In this book, we get an uncensored excursion into the mind of genius - which is, without doubt, a fascinating prospect. The book consists of a collection of essays and speeches that Wolfram has produced over the last ten to fifteen years, covering an eclectic range of topics. Like all such collections, the result is something that lacks the coherence of a book with a narrative that runs through it, inevitably introducing a degree of repetition and a mix of interesting and not-so-interesting topics - but there's likely to be something to catch the attention anyone who is into computing or mathematics. One of the most interesting pieces is the opening one, where Wolfram describes being a consultant on the SF movie Arrival. He seems to hav...
Post a Comment
Read more

E=mc2: A biography of the world’s most famous equation – David Bodanis *****

David Bodanis is a storyteller, and he fulfils this role with flair in E=mc2. The premise of the book is simple – Einstein himself has been biographed (biographised?) to death, but no one has picked out this most famous of equations, dusted it down and told us what it means, where it comes from and what it has delivered. Allegedly, Bodanis was inspired to write the book after hearing see an interview with actress Cameron Diaz in which she commented that she’d really like to know what that famous collection of letters was all about. Although the book had been around for a while already when this review was written (September 2005), it seemed a very apt moment to cover it, as the equation is, as I write, exactly 100 years old. So when better to have a biography? Bodanis starts off by telling us about the individual elements of the equation. What the different letters mean, where the equal sign comes from and so on. This is entertaining, though he seems to tire of the approach on...
Post a Comment
Read more