Abstract Details
Activity Number:
|
350
|
Type:
|
Contributed
|
Date/Time:
|
Tuesday, August 5, 2014 : 10:30 AM to 12:20 PM
|
Sponsor:
|
Biopharmaceutical Section
|
Abstract #312508
|
|
Title:
|
Defining Geographic Regions with a Data Mining Approach
|
Author(s):
|
Ziliang Li*+
|
Companies:
|
Merck
|
Keywords:
|
data mining ;
dynamic time warping ;
clustering ;
regional variation
|
Abstract:
|
Regional variations in population characteristics and efficacy measurements are common in late phase clinical trials. To account for such variations, investigative sites are typically pre-specified to regions based on certain geographical and environmental conventions (e.g., North America, South America and Europe, urban or suburb area, etc.) and the analysis model adjusts for the region factor. Such classifications have practical advantages, but one main drawback is that the classification is static in nature. In situations where subjects' characteristics and/or efficacy measurements are affected by ongoing or long term fluctuations of environmental factors, such as temperature, concentration of pollutant and changes of ecological system near subjects' dwelling, a data driven classification of regions can be more desirable. In this presentation, I will demonstrate using the dynamic time warping (DTW) algorithm and selected clustering approaches to re-assign investigative sites to artificial regions, using daily environmental readings collected in a recent clinical trial. It is shown that re-defining regions based on the non-efficacy related environmental readings better capture th
|
Authors who are presenting talks have a * after their name.
Back to the full JSM 2014 program
|
2014 JSM Online Program Home
For information, contact jsm@amstat.org or phone (888) 231-3473.
If you have questions about the Professional Development program, please contact the Education Department.
The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.
Copyright © American Statistical Association.