This is an archived version of the Handbook. For the current version, please go to or search for this chapter here.  Warning: counting events or counting participants?

A common error is to attempt to treat count data as dichotomous data. Suppose that in the example just presented, the 314 person-years arose from 157 patients observed on average for 2 years. One may be tempted to quote the results as 18/157. This is inappropriate if multiple MIs from the same patient could have contributed to the total of 18 (say if the 18 arose through 12 patients having single MIs and 3 patients each having 2 MIs). The total number of events could theoretically exceed the number of patients, making the results nonsensical. For example, over the course of one year, 35 epileptic participants in a study may experience 63 seizures among them.