2. Mean follow-up was 3·5 years (SD 2·0). One last time for an old favourite: what can we deduce about the distribution of follow-up time? Why should the follow-up times vary so much?
If the distribution were symmetrical, we would expect some observations to be smaller than the mean minus two standard deviations. Because the standard deviation is more than half the mean, such observations would be negative. Follow-up time cannot be negative, so the observations which are more than two standard deviations from the mean must all be in the upper tail of the distribution. Therefore, the distribution must be positively skew or skew to the right.
Follow-up times vary because the patients are recruited over the period of the trial, several years, and all followed up to the end of the trial. Some patients therefore have much longer follow-up times than others.
Back to question.
Back to Biostatistics in Research Practice index.
This page maintained by Martin Bland.
Last updated: 5 April, 2007.