Skip navigation

Chance and choice in an evidence-based society

Mad cows and ecstasy

The headline of this article could well have been written by the Bandolier editorial team, combining as it does elements of science and showbiz. It is, however, the title of a major paper in that most respectable of journals, the Journal of the Royal Statistical Society.

The title was chosen by Adrian Smith for his Presidential address [1] and provides an excellent overview of all the issues about which Bandolier cares so dearly.

Professor Smith laments the image of statistics as mere number-crunching and prefers to say that statistics is "the science of doing science". It will be encouraging to doctors, frequently criticised for not practising evidence-based health care, to learn that medicine stands out like a shining beacon in a world of evidence-based decision-making. Doctors will regard with some relish Professor Smith's lambasting of the legal profession and he quotes a depressing comment from the Bench of the Court of Appeal:

"Evidence of the Bayes Theorem or any similar statistical method of analysis in a criminal trial plunged the jury into inappropriate and unnecessary realms of theory and complexity, deflecting them from their proper task...Their Lordships ....had very grave doubts as to whether that evidence was properly admissible because it trespassed on an area peculiarly and exclusively within the jury's province, namely the way in which they evaluated the relationship between one piece of evidence and another. The Bayes Theorem might be an appropriate and useful tool for statisticians, but it was not appropriate for us in jury trials or as a means to assist the jury in its task "[2].


So there we have it, as Professor Smith says. To hell with rationality as we know it - their Lordships have pronounced!

Showing just how broad the view of a statistician actually is, the author presents fascinating issues about chance and choice, looking at sociological obstacles to evidence-based health care, principally the problems of translating decisions about groups (the basis of epidemiology) to decisions about individuals (the core business of clinical practice). Psychological obstacles and issues are also discussed and his section on risk shows just how illogical we are in assessing risks - as the table shows.

To prevent these problems he advocates better education but emphasises the size of the task that faces us. He also challenges statisticians to play a bigger part in debates dominated by opinion, prejudice, and sometimes hysteria, most recently the debates on mad cows and ecstasy. He finishes with a wonderful quote about Florence Nightingale (at a time when she was injecting morphine for her back pain - Bandolier ed):

"Florence Nightingale believed - and in all the actions of her life acted on that belief - that the administrator could only be successful if he (she) were guided by statistical knowledge. The legislator - to say nothing of the politician - too often failed for want of this knowledge. Nay, she went further: she held that the universe - including human communities - was evolved in accordance with a divine plan.....But to understand God's thoughts, she held we must study statistics, for these are the measures of His purpose. Thus the study of statistics was for her a religious duty".
Karl Pearson


Request this article from your library: it is a classic, and great reading for the beach at Blackpool or a cafe in the Dordogne.

References:

  1. AFM Smith. Mad cows and ecstasy: chance and choice in an evidence-based society. Journal of the Royal Statistical Association 1996; 159: 367-83.
  2. The Times. Juries not to apply mathematical formulae. May 9 1996.



previous or next story in this issue