Survival probabilities (the Kaplan-Meier method)

doi:10.1136/bmj.317.7172.1572

From trainee to consultant, BMJ Group offers doctors around the world tailored information, special events, learning resources and recruitment services at every step along their career path.

... by doctors, for doctors, for patients
We are open for entries!

Online learning

BMJ Learning

High-quality CME / CPD for doctors and other healthcare professionals. BMJ Learning features hundreds of accredited, peer-reviewed learning modules in text, video, and audio formats. Find out more

Courses and Qualifications

BMJ Masterclasses

BMJ Masterclasses, led by experts, help clinicians to use the latest evidence and recent guidelines in practice and meet their CPD/CME requirements. Find out more

Exam Preparation

The leading provider of online exam preparation, helping over 167,000 healthcare professionals to pass their exams. Find out more

onExamination

Search all BMJ education articles:

From

Limit by

The BMJ iPad app brings you the best of print and online, including live links to the latest news, blogs, video, and podcasts. Get the BMJ iPad app.
You can use bmj.com to help you with your continuing medical education. Find out about CME/CPD credits for BMJ articles
Keep up to date with cardiology: Access the latest cardiovascular medicine resources from across BMJ Group.
Countdown to London 2012: BMJ Group's Olympics portal highlights latest Olympics and sports medicine-themed research, comment and learning

Access to the full text of this article requires a subscription or payment. Please log in or subscribe below.

J Martin Bland, professor of medical statisticsa,
Douglas G Altman, headb

Department of Public Health Sciences, St George's Hospital Medical School, London SW17 0RE
ICRF Medical Statistics Group, Centre for Statistics in Medicine, Institute of Health Sciences, Oxford OX3 7LF

aCorrespondence to: Professor Bland

As we have observed,1 analysis of survival data requires special techniques because some observations are censored as the event of interest has not occurred for all patients. For example, when patients are recruited over two years one recruited at the end of the study may be alive at one year follow up, whereas one recruited at the start may have died after two years. The patient who died has a longer observed survival than the one who still survives and whose ultimate survival time is unknown.

The table shows data from a study of conception in subfertile women.2 The event is conception, and women “survived” until they conceived. One woman conceived after 16 months (menstrual cycles), whereas several were followed for shorter time periods during which they did not conceive; their time to conceive was thus censored.

View this table: