Related Experiment Video
Updated: Jun 26, 2026

Estimating Virus Production Rates in Aquatic Systems
Published on: September 22, 2010
Events per person-time (incidence rate): a misleading statistic?
1Department of Psychiatry and Behavioral Sciences, Stanford University, Stanford, CA 943305, USA. hckhome@pacbell.net
Abstract:
Results in risk studies based on events per person-time (EPT, technically 'incidence rate') often prove non-confirmable. The circumstances in which the EPT-ratio is unquestionably both valid and optimal to compare a high- and low-risk group, a constant hazards situation, are discussed. However, the constant hazards situation seldom applies in medical research. When the constant hazards situation does not apply, even under optimal circumstances, with fixed entry time and follow-up time for all those not experiencing the event and absence of censoring, EPT-ratio yields at best ambiguous, at worst misleading, results. More careful design and survival analyses are recommended in place of use of EPTs.
Related Concept Videos
Prevalence and Incidence
Prevalence indicates the proportion of individuals in a population who have a specific disease or health condition at a...
The Availability Heuristic
Bias in Epidemiological Studies
Confounding in Epidemiological Studies
Hazard Rate
Causality in Epidemiology
