|
Activity Number:
|
198
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Monday, July 30, 2007 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Biopharmaceutical Section
|
| Abstract - #309279 |
|
Title:
|
A Comparison of Imputation Methods in a Randomized Active Comparator Pain Relief Clinical Trial
|
|
Author(s):
|
Adam Hamm*+
|
|
Companies:
|
Rho, Inc.
|
|
Address:
|
6330 Quadrangle Drive, Chapel Hill, NC, 27517,
|
|
Keywords:
|
Missing Data ; BLUPs ; Imputation
|
|
Abstract:
|
We evaluate the properties of a mixed model analysis with various imputation methods for handling missing data in a randomized, double-blind active comparator Phase III trial evaluating the efficacy of a pain relief treatment. We discuss a method for generating a dataset with complete outcome measures over time based on the results of an analysis of available blinded data, and then use this complete dataset to compare the various methods of imputation and determine the bias of each method under different assumptions for possible treatment effect. The baseline observation carried forward (BOCF) and last observation carried forward (LOCF) imputation methods are contrasted with an analysis of the available data (AVAL), an analysis that imputes missing data via a method of generating empirical best linear unbiased predictors (BLUP), and an analysis of the simulated complete dataset.
|
- 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 2007 program |
