Abstract #300435

This is the preliminary program for the 2003 Joint Statistical Meetings in San Francisco, California. Currently included in this program is the "technical" program, schedule of invited, topic contributed, regular contributed and poster sessions; Continuing Education courses (August 2-5, 2003); and Committee and Business Meetings. This on-line program will be updated frequently to reflect the most current revisions.

To View the Program:
You may choose to view all activities of the program or just parts of it at any one time. All activities are arranged by date and time.

The views expressed here are those of the individual authors
and not necessarily those of the ASA or its board, officers, or staff.

Back to main JSM 2003 Program page
JSM 2003 Abstract #300435
Activity Number: 421
Type: Contributed
Date/Time: Wednesday, August 6, 2003 : 2:00 PM to 3:50 PM
Sponsor: Biopharmaceutical Section
Abstract - #300435
Title: A General Approach to Improve Inference at Interim: Beyond Point Estimation
Author(s): Brenda L. Gaydos*+
Companies: Eli Lilly & Company
Address: Lilly Corporate Center, Indianapolis, IN, 46285-0001,
Keywords: interim inference ; confidence Interval ; resampling
Abstract:

One objective of interim analyses in early stage clinical development is internal project planning. In this scenario, based on the observed data, it is necessary to estimate the probability of achieving success on a simple or complex set of future event outcomes. A versatile method that can provide both a point estimate and an estimate of precision of that point estimate would enable teams to better quantify risk and make inference. Typical approaches, such as conditional power, are limited in their ability to estimate a complex set of outcomes and do not provide a ready measure of precision. A new approach, based on augmenting the observed data with an estimate of future data through resampling will be presented. Due to the conditional approach, resampling theory based on independent sampling does not directly apply. Two examples will be shared from Phase II/III clinical trials where this new approach has been implemented. The dependent variable in Case 1 follows a normal distribution, and in Case 2 a binomial distribution. Results will be compared to a traditional conditional power approach.

  • The address information is for the authors that have a + after their name.
  • Authors who are presenting talks have a * after their name.

Back to the full JSM 2003 program

JSM 2003 For information, contact meetings@amstat.org or phone (703) 684-1221. If you have questions about the Continuing Education program, please contact the Education Department.
Revised March 2003