Premium
Sample size calculation for clinical trials in which entry criteria and outcomes are counts of events
Author(s) -
McMahon Robert P.,
Proschan Michael,
Geller Nancy L.,
Stone Peter H.,
Sopko George
Publication year - 1994
Publication title -
statistics in medicine
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.996
H-Index - 183
eISSN - 1097-0258
pISSN - 0277-6715
DOI - 10.1002/sim.4780130806
Subject(s) - sample size determination , poisson regression , statistics , medicine , poisson distribution , clinical trial , regression , regression toward the mean , linear regression , mathematics , population , environmental health
In many chronic diseases, therapy aims to prevent or reduce the frequency of episodes of a disease manifestation, for example cardiac ischaemic episodes or epileptic seizures. Entry criteria for clinical trials typically include a minimum number of episodes within a baseline period, and regression to the mean should be anticipated. The distribution of the number of episodes at follow‐up, the statistical power for treatment comparisons, and the difficulty of recruitment will depend on the entry criterion chosen. A gamma‐Poisson mixture model is employed to describe the regression to the mean when the entry criterion and outcome measure are counts of discrete events. Sample size formulae which take account of the entry criterion are derived for comparison of mean number of events at follow‐up and the proportion of patients with zero events at follow‐up. Application of these formulae to screening data from the Aymptomatic Cardiac Ischemia Pilot (ACIP) Study is presented as an example.