|
Activity Number:
|
221
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, August 10, 2004 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Biopharmaceutical Section
|
| Abstract - #301393 |
|
Title:
|
Fieller's Theorem with Its Applications in Clinical Trials
|
|
Author(s):
|
Pam Launt*+ and Chunqin Deng
|
|
Companies:
|
PPD Development, Inc. and PPD Development, Inc.
|
|
Address:
|
192 Hestia Dr., Plainwell, MI, 49080,
|
|
Keywords:
|
Fieller's theorem ; confidence interval ; relative potency
|
|
Abstract:
|
There are a lot of situations under which a ratio needs to be calculated to represent a quantity. While the estimate for this ratio is relatively straightforward, the confidence interval for the estimate of the ratio may not be easy to compute and some alternative ways may need to be employed to obtain the confidence interval. Fieller's theorem is one of the alternatives that can provide confidence intervals for the ratio of mean values of two random variables having a bivariate normal distribution. According to Fieller's theorem, if the variance and covariance for numerator and denominator of the ratio are known, the confidence interval can be obtained by solving a quadratic inequality function. Fieller's theorem has been often used for constructing the confidence intervals for a ratio in clinical trials, bioassay, and environmental statistics. To illustrate the application of Fieller's theorem in clinical trial, three examples are given: confidence interval for the incremental cost-effectiveness ratio (ICER) in health economic area; confidence interval for relative potency in a phase III clinical trial; and the confidence interval used in a bioequivalence test.
|
- 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 2004 program |
