 |
The 130th Annual Meeting of APHA |
|
The 130th Annual Meeting of APHA |
Jichuan Wang, Community Health Dept., Wright State University, 3640 Colonel Glenn Hwy, Dayton, OH 45435, 937 775-2084, jichuan.wang@wright.edu
In longitudinal studies, a common problem is attrition; and very often, attrition is non-random. That is, the dropouts in the follow-up interviews are disproportional across treatment tracks, as well as by age, gender, or ethnicity groups. As a result, the observed change in an outcome measure between the baseline and any specific follow-up interview could be confounded by changes in the compositions of the sample. This study employs the standardization and decomposition methods to examine how much of the changes in measures of substance abuse and HIV risk behaviors over a three year period in a sample of crack-cocaine users were due to the "real" change in the outcome measures; and how much were due to changes in sample compositions, caused by non-random attrition. A computer program, DECOMP, developed by the author, will be demonstrated.
Learning Objectives:
Keywords: Methodology, Change
Related Web page: www.wright.edu\~jwang
Presenting author's disclosure statement:
I do not have any significant financial interest/arrangement or affiliation with any organization/institution whose products or services are being discussed in this session.