Sample Size: Negative Binomial With Unequal Follow-Up Times

Authored by: Yongqiang Tang

Encyclopedia of Biopharmaceutical Statistics

Print publication date:  August  2018
Online publication date:  August  2018

Print ISBN: 9781498733953
eBook ISBN: 9781351110273
Adobe ISBN:


 Download Chapter



Recurrent events are common in clinical trials. Examples include exacerbations in chronic obstructive pulmonary disease, relapses in multiple sclerosis, seizures in epileptics, and hospitalizations. In late-phase confirmatory trials, the primary endpoint is generally the total number of events experienced by the subjects. The recurrent event counts often exhibit overdispersion, in the sense, that the variance exceeds the mean. Negative binomial (NB) regression has become widely used to analyze recurrent event data in clinical trials since it provides a natural way to account for overdispersion. Several previously developed methods for calculating sample size for the NB regression assume equal follow-up time for all subjects by ignoring early dropouts or by setting the follow-up time for all individuals to be the mean follow-up time. Ignoring variability in the duration of the follow-up generally leads to underpowered studies. In this entry, we review the sample size calculation methods for comparing two NB rates in superiority, non-inferiority, and equivalence trials with unequal follow-up times.

Search for more...
Back to top

Use of cookies on this website

We are using cookies to provide statistics that help us give you the best experience of our site. You can find out more in our Privacy Policy. By continuing to use the site you are agreeing to our use of cookies.