|
Reckoning with Risk: Learning to Live with Uncertainty
|
| Price: |
7 new or used available from £4.62
Average customer review:
Product Description
In the beginning of the 20th century, the father of modern science fiction, H.G. Wells, predicted that statistical thinking would be as necessary for citizenship in a technological world as the ability to read and write. Yet, a century on, most of us, from TV weather forecasters to the American President, seem to have no idea of how to reason about uncertainties. This volume offers a treatment for the "disease" of statistical illiteracy. Aimed at helping us understand risks in the real world, it shows how a proper understanding of uncertainties can make the difference between hope and despair.
Product Details
- Amazon Sales Rank: #285853 in Books
- Published on: 2002-07-04
- Original language: English
- Binding: Paperback
- 320 pages
Editorial Reviews
About the Author
Gerd Gigerenzer is Director of the Center for Adaptive Behaviour and Cognition in Berlin, and a former Professor of Psychology at the University of Chicago. Dan Dennett writes: "Gigerenzer is one of the smartest psychologists I know, and he's bursting with great ideas. His topic is dynamite".
Customer Reviews
Interesting but a bit repetitive
I picked up this book because it was short-listed for the Aventis science prize. It is an interesting book that aims to assist the reader in becoming literate in the sort of risk assessment statistics we encounter all the time e.g. 'this drug reduces your risk of heart disease over 10 years by 50%'. It focuses on understanding conditional probabilities, using natural frequencies to assess uncertainty and the difference between absolute and relative risks.
Although it does help you to understand everyday statistics of this nature better, it only appears to make about 3 points throughout the entire book. Most of the chapters just recycle the same ideas using various, mainly medical, examples. A punchy 20 page book would have been just as informative, less repetitive and thus more interesting and effective.
An essential contribution to public education
I bought this book to while away time on a plane journey to the USA on holiday, and liked it so much that when I was asked to give an informal introductory Stats talk to a group of doctors in New York, I recommended it to them and worked through the example in Fig 4-2.
The book does a very good job of explaining Franklin's Law (nothing is certain except death and taxes), illustrating it with important problems like HIV tests and DNA testing. The idea that even DNA tests are not infallible will come as news to some! It also discusses cost-benefit issues in diagnostic tests and the way to explain risk in a way that is not misleading, specifically emphasising the value of ARR and NNT over RR reduction.
All in all, the book seems to me an essential contribution to public education, especially for doctors and lawyers.
Most highly recommended.
essential reading
This book is the perfect antidote to the mistakes of reasoning we are all prone to, when faced with uncertainty and rare events. It offers itself as a way of turning ignorance into insight, and follows through on the offer.
What if you have a positive mammogram, or test positive for HIV? Do you know how likely it is that you have actually got breast cancer, or that you are indeed HIV positive? Most of us don't have the foggiest, yet this is the sort of information we all need desperately.
There is a simplification at the heart of the book - not all statistical information can be summarised effectively using natural frequencies - and the author is not a mathematician and gives no sign that he understands that this is a simplification. But often enough natural frequencies will do the trick, and you will find no better explanation of how to think than this book.
What can I say? Everyone should read it. That means you!
