Test-subject objections

November 15, 2012

So the University of Aberdeen has developed a test for schizophrenia that is 98 per cent accurate (Campus round-up, 8 November). Should I be worried if I test positive?

Around 1 per cent of the population has schizophrenia, so in a sample of 10,000 you will get 98 of the 100 with schizophrenia correctly testing positive. However, 2 per cent of the 9,900 - 198 - who haven't got it will also test positive. Therefore, the probability of a positive test being correct is 98/(98+198), or 33 per cent. So, more than two-thirds of those positively diagnosed by the test will in fact not be schizophrenic. Reassuringly high accuracy rates are meaningless unless one knows the prevalence of what is being tested.

Hillary J. Shaw, Senior lecturer, Department of food and supply chain management, Harper Adams University College

You've reached your article limit.

Register to continue

Registration is free and only takes a moment. Once registered you can read a total of 3 articles each month, plus:

  • Sign up for the editor's highlights
  • Receive World University Rankings news first
  • Get job alerts, shortlist jobs and save job searches
  • Participate in reader discussions and post comments

Have your say

Log in or register to post comments

Featured Jobs

Most Commented

Monster behind man at desk

Despite all that’s been done to improve doctoral study, horror stories keep coming. Here three students relate PhD nightmares while two academics advise on how to ensure a successful supervision

Sir Christopher Snowden, former Universities UK president, attacks ratings in wake of Southampton’s bronze award

opinion illustration

Eliminating cheating services, even if it were possible, would do nothing to address students’ and universities’ lack of interest in learning, says Stuart Macdonald

Female professor

New data show proportion of professors who are women has declined at some institutions

celebrate, cheer, tef results

Emilie Murphy calls on those who challenged the teaching excellence framework methodology in the past to stop sharing their university ratings with pride