Abstract
I describe methods of analysing possible aetiological factors in a follow‐up survey, all of which are possible to carry out using the statistical package GENSTAT. A high haemoglobin level carried a significantly increased risk of ischaemic heart disease, and a low one an increased risk of cancer. Smoking was also an important factor. The increased risk was reasonably constant over time. Sugar intake and Quetelet's index did not significantly affect the relative risk.

This publication has 9 references indexed in Scilit: