This paper explores event data as an abstract statistical object. It b
riefly traces the historical development of event data, with particula
r attention to how nominal events have come to be used primarily in in
terval-level studies. A formal definition of event data and its stocha
stic error structure is presented. From this definition, some concrete
suggestions are made for statistically compensating for misclassifica
tion and censoring errors in frequency-based studies. The paper argues
for returning to the analysis of events as discrete structures. This
type of analysis was not possible when event data were initially devel
oped, but electronic information processing capabilities have improved
dramatically in recent years and many new techniques for generating a
nd analyzing event data may soon be practical.