|
Activity Number:
|
154
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Monday, July 30, 2007 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Biopharmaceutical Section
|
| Abstract - #308356 |
|
Title:
|
Application of Principal Component Analysis in the Reduction of a 19-Item Clinical Scale
|
|
Author(s):
|
Hong Liu-Seifert*+
|
|
Companies:
|
Eli Lilly and Company
|
|
Address:
|
Lilly Corporate Center, Indianapolis, IN, 46285,
|
|
Keywords:
|
Principal Component Analysis ; factors ; data reduction
|
|
Abstract:
|
Rating of Medication Influence (ROMI) is a 19-item clinical scale. Its use has been limited due to the large number of items and lack of established structure. The objective of this research was to apply Principal Component Analysis (PCA) to explore the underlying dimensions of ROMI. PCA was applied to ROMI from 2 studies with different designs and patient populations. Further, factors were derived at multiple time points and for each treatment arm for sensitivity. PCA yielded largely identical factors for ROMI for the 2 studies. These factors were consistent with the commonly accepted Health Belief Model. Results were also consistent at different time points and for each treatment group in each study. The derived factor structure for ROMI based on PCA is robust and may facilitate the use of ROMI as an easy and more applicable rating scale with reduced dimensions.
|
