Premium
Group sequential procedures: Calendar versus information time
Author(s) -
Lan K. K. Gordon,
Demets David L.
Publication year - 1989
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.4780081003
Subject(s) - interim , group (periodic table) , computer science , prior information , interim analysis , statistics , operations research , clinical trial , medicine , mathematics , artificial intelligence , history , chemistry , archaeology , organic chemistry
This paper describes the relationship between information time and calendar time in the use of group sequential procedures to monitor interim analyses of clinical trials. Information time is the proportion of maximum subjects or events already observed. Interim analyses often occur at specified calendar times while the definition of classic group sequential procedures occurs in terms of information time. We extend the general group sequential approach of Lan and DeMets 1 to include this situation as well.