NEW PSYCHOMETRIC METHODS FOR SUBSTANCE ABUSE RESEARCH

点击翻译按钮获取中文摘要

DESCRIPTION: (Applicant's Abstract) This is a request for a K05 Senior Scientist Research Career Award (RCA) as a competing continuation of #5 KO5 DAOOO17. The specific aims of the proposed five-year research program are the following: 1. Develop new psychometric methods for drug abuse, AIDS, and policy research 2. Apply these newly developed methods to important drug abuse data sets 3. Generate nontechnical papers and practical improvements in methodology, 4. Create tutorials to improve methodology in drug abuse research, and 5. Advise drug abuse and health researchers and government agencies on methodology The research program is directed towards the development of new multivariate psychometric and statistical techniques that hold special promise for improving the quality of psychosocial, social, behavioral, epidemiological, and health-related research on drug use and abuse and AIDS related behaviors. Methods for robustly analyzing experimental and nonexperimental drug abuse data that may contain selectivity, outlier cases, arbitrary distributions, errors in-measurement, ordinal scales, nonstandard sampling plans, etc. will be developed. Special attention is given to structural equation models that may involve latent variables in mediation and moderator relations. Optimal missing data, robust, distribution-free, and policy research methods are a special focus. While no data will be gathered under this grant, the newly developed techniques will be extensively evaluated for their practical relevance to drug abuse/AIDS research by addressing important substantive issues in drug abuse on high-quality data obtained in association with NIDA/UCLA program project grant PO1 DA01070 via collaboration with nationally active substance abuse researchers working on their own projects, as well as by cooperation with NIDA and other health-related agencies. Methods that are developed under this grant also will be widely disseminated via goals (3) and (4) above.