## Dicing with Death: Chance, Risk and HealthIf you think that statistics has nothing to say about what you do or how you could do it better, then you are either wrong or in need of a more interesting job. Stephen Senn explains here how statistics determines many decisions about medical care--from allocating resources for health, to determining which drugs to license, to cause-and-effect in relation to disease. He tackles big themes: clinical trials and the development of medicines, life tables, vaccines and their risks or lack of them, smoking and lung cancer and even the power of prayer. He entertains with puzzles and paradoxes and covers the lives of famous statistical pioneers. By the end of the book the reader will see how reasoning with probability is essential to making rational decisions in medicine, and how and when it can guide us when faced with choices that impact our health and/or life. Stephen Senn has been a Professor of Pharmaceutical and Health Statistics at the University College of London since 1995. In 2001 he won George C. Challis Award of the University of Florida for contributions to biostatistics. Senn's previous two books are Statistical Issues in Drug Development (Wiley, 1997) and Cross-over Trials in Clinical Research (Wiley, 1993). He is the member of seven editorial boards including Statistics in Medicine and Pharmaceutical Statistics. |

### What people are saying - Write a review

#### LibraryThing Review

User Review - Coobeastie - LibraryThingI like this book, but I can only give it a low star rating. It's a complex subject, but well handled by the author. The problem is the number of typos! I studied this book as part of an Open ... Read full review

### Other editions - View all

### Common terms and phrases

accidents already alternative analysis answer appears apply approach assume average Bayesian births born calculate called cancer cause chance Chapter clinical trial Cochrane coin compared condition consider contributions course deaths developed difference disease distribution effect equal error evidence example expected experiments fact females Figure Fisher four further give given heads Health hypothesis important increase individual infected interest Journal least less London look males mathematician mathematics matter mean measure medicine observed obtain original particular patients Pearson period physician Poisson population position possible probability problem question random randomised ratio reason referred regarded relevant Royal sequence significance Society sort standard statistician statistics Suppose Table tail theory tion tosses treat treatment true turns University vaccine women