|
Activity Number:
|
125
|
|
Type:
|
Invited
|
|
Date/Time:
|
Monday, August 7, 2006 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Biopharmaceutical Section
|
| Abstract - #305249 |
|
Title:
|
The Impact of Missing Data and How It Is Handled on the Rate of False Positive Results in Drug Development
|
|
Author(s):
|
Stacy Lindborg*+ and Craig Mallinckrodt and Michael K. Carter and Sunni A. Barnes+
|
|
Companies:
|
Eli Lilly and Company and Eli Lilly and Company and Eli Lilly and Company and KCI
|
|
Address:
|
Lilly Corporate Center, Indianapolis, IN, 46285, 6203 Fairnon Drive, San Antonio, TX, 78249,
|
|
Keywords:
|
missing data ; regulatory risk ; Bayesian ; multiple imputation ; MMRM
|
|
Abstract:
|
In drug development a common choice for the primary analysis is to assess mean changes via analysis of (co)variance with missing data imputed by carrying the last or baseline observations forward (LOCF, BOCF). These approaches assume data are missing completely at random (MCAR). Multiple imputation (MI) and likelihood-based repeated measures (MMRM) are less restrictive as they assume data are missing at random (MAR). We report results from a simulation study that compared the rate of false positive results from LOCF, BOCF, MI, and MMRM. These results illustrate the MAR methods provide better control of false positive rates than the MCAR methods. We discuss the need for and benefit from using MAR methods as the primary analysis in drug development.
|
