American Statistical Association
New York City
Metropolitan Area Chapter

Mailman School of Public Health
Columbia University
Department of Biostatistics Colloquium



Dr. Edward Lakatos
BiostatHaven Inc


Sample size re-estimation was introduced to increase the likelihood of a successful trial. However, logistic issues associated with increasing the sample size of a trial based on interim data have hampered its use. Because continuation of a trial beyond the current interim of a group sequential design is routine, the same logistic issues do not usually pose a problem. However, group-sequential trials were not introduced to address the primary goal of sample size re-estimation. One way to enhance the sample size re-estimation objective within the group-sequential paradigm is to optimize the design for a range of alternatives. I begin with a discussion of why the typical approach to optimization of group-sequential boundaries is problematic and propose an alternate set of optimality criteria. Using a recently designed trial as an example, I discuss how to obtain estimates of the hazard function for the new trial from prior trial results. I then explain how Markov models can be used to construct boundaries that address the new optimality criteria relative to the estimated hazard function and the chosen range of alternatives.

Date: Thursday, November 13, 2008
Time: 4:00 - 5:00 P.M.
Location: Mailman School of Public Health
Department of Biostatistics
722 West 168th Street
Biostatistics Computer Lab
6th Floor - Room 656
New York, New York


Refreshments will be served at 3:30 P.M. in the
Biostatistics Conference Room (R627).

Home Page | Chapter News | Chapter Officers | Chapter Events
Other Metro Area Events | ASA National Home Page | Links To Other Websites
NYC ASA Chapter Constitution | NYC ASA Chapter By-Laws

Copyright © 2008 by New York City Metropolitan Area Chapter of the ASA
Designed and maintained by Cynthia Scherer
Send questions or comments to