Online Program Home
  My Program

Abstract Details

Activity Number: 664 - Three Pillars of Successful Health Studies: Inclusion, Design, and Measurement
Type: Contributed
Date/Time: Thursday, August 3, 2017 : 10:30 AM to 12:20 PM
Sponsor: Health Policy Statistics Section
Abstract #324089
Title: Data Harmonization and Common Measure Construction in HIV Adherence Studies
Author(s): Yan Wang*
Companies: UCLA
Keywords: Harmonization ; Quality ; Adherence ; Visualization ; Common measure
Abstract:

Hamming distance is used to describe the similarity between data sets. None studies measure the similarity by taking consideration of study designs before merging studies together. We use hamming distance and pre-distance matrix to determine the harmonizability among studies. The harmonization circle is invented to visualize the harmonization among the studies and the harmonization scores are generated, which could be used later to compare whether the studies are relatively comparable and could be harmonized together to answer a pre-determined question. Graph theory is applied to quantify the harmonization circle in metric theory. The weight distance is used in generalizing the pre-distance matrix. The inverse of the matrix could be applied to harmonizable measures to create the common measure. The theory has been applied to a real study to create a common measure based on the harmonization score from multiple studies that use different instruments to measure depression. This harmonized measure with large sample size database could be used to answer more complicated questions, controlling for confounders. The method is also compared with traditional Z score transformation.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2017 program

 
 
Copyright © American Statistical Association