Approaches for creating comparable measures of alcohol use symptoms: Harmonization with eight studies of criminal justice populations
•Moderated nonlinear factor analysis is a tool for pooled analysis.•MNLFA scores had more desirable properties than pooled cut-scores and sum scores.•MNLFA scores showed strongly predictive validity than other scores.•MNLFA is a promising tool for harmonization in pooled data analysis.. With increas...
Saved in:
| Published in | Drug and alcohol dependence Vol. 194; pp. 59 - 68 |
|---|---|
| Main Authors | , , , , , , , , , , , , , , , , , , |
| Format | Journal Article |
| Language | English |
| Published |
Ireland
Elsevier B.V
01.01.2019
Elsevier Science Ltd |
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Summary: | •Moderated nonlinear factor analysis is a tool for pooled analysis.•MNLFA scores had more desirable properties than pooled cut-scores and sum scores.•MNLFA scores showed strongly predictive validity than other scores.•MNLFA is a promising tool for harmonization in pooled data analysis..
With increasing data archives comprised of studies with similar measurement, optimal methods for data harmonization and measurement scoring are a pressing need. We compare three methods for harmonizing and scoring the AUDIT as administered with minimal variation across 11 samples from eight study sites within the STTR (Seek-Test-Treat-Retain) Research Harmonization Initiative. Descriptive statistics and predictive validity results for cut-scores, sum scores, and Moderated Nonlinear Factor Analysis scores (MNLFA; a psychometric harmonization method) are presented.
Across the eight study sites, sample sizes ranged from 50 to 2405 and target populations varied based on sampling frame, location, and inclusion/exclusion criteria. The pooled sample included 4667 participants (82% male, 52% Black, 24% White, 13% Hispanic, and 8% Asian/ Pacific Islander; mean age of 38.9 years). Participants completed the AUDIT at baseline in all studies.
After logical harmonization of items, we scored the AUDIT using three methods: published cut-scores, sum scores, and MNLFA. We found greater variation, fewer floor effects, and the ability to directly address missing data in MNLFA scores as compared to cut-scores and sum scores. MNLFA scores showed stronger associations with binge drinking and clearer study differences than did other scores.
MNLFA scores are a promising tool for data harmonization and scoring in pooled data analysis. Model complexity with large multi-study applications, however, may require new statistical advances to fully realize the benefits of this approach. |
|---|---|
| Bibliography: | ObjectType-Article-2 SourceType-Scholarly Journals-1 ObjectType-Feature-1 content type line 23 Sandra Springer, Yale School of Medicine, Section of Infectious Diseases, Yale AIDS Program, 135 College Street, Suite 323, New Haven, CT 06510, USA, sandra.springer@yale.edu Nisha Gottfredson, 319C Rosenau Hall, CB #7440, Chapel Hill, NC 27599, USA, gottfredson@unc.edu Quan, Johns Hopkins University, Center for Global Health, 415 N Washington St. Rooms 333–341, Baltimore, MD 21205, USA, vquan1@jhu.edu Daniel Feaster, 1120 N.W. 14th Street, Clinical Research Building – Room 1064, Miami, Florida 33136, USA, dfeaster@biostat.med.miami.edu Shoshana Kahana, Division of Biomedical Research Workforce, Office of Extramural Research, Office of the Director, National Institutes of Health, 6705 Rockledge Drive, Room 3534, Bethesda, MD 20892-7963, USA, shoshana.kahana@nih.gov Michael Gordon, Friends Research Institute, Inc., 1040 Park Avenue, Suite 103, Baltimore, MD 21201, USA, mgordon@friendsresearch.org Contributors have all substantively added to the manuscript through a coordinated publications process associated with the STTR collaborative either through analyses, manuscript review, data coordination, hypotheses generation, and interpretation of findings. All authors have approved the final article. Redonna K. Chandler, National Institute on Drug Abuse, 6001 Executive Boulevard, Room 5265, Rockville, MD 20892-9581, USA, redonna.chandler@nih.gov Author Contact Information Patrick M. Flynn, Institute of Behavioral Research, Texas Christian University, TCU Box 298740, Fort Worth, TX 76129, USA, ibr@tcu.edu Frederick Altice, Yale University AIDS Program, 135 College Street, Suite 323, New Haven, CT 06510-2283, USA, frederick.altice@yale.edu Joseph A (Chris) Delaney, Research Associate Professor, Department of Epidemiology, University of Washington, USA, jacd@uw.edu Irene Kuo, George Washington University, Milken Institute School of Public Health, 950 New Hampshire Avenue NW, Suite 500, Washington, DC 20052, ikuo@gwu.edu Lawrence J. Ouellet, Epi/Bio/COIP, School of Public Health (MC 923), University of Illinois at Chicago, 1603 W. Taylor Street, Chicago, IL 60612, USA, ljo@uic.edu David Seal, 1440 Canal Street, Suite 2200, Mailstop #8319, Office 2224, New Orleans, LA 70112, USA, dseal@tulane.edu Andrea M. Hussong, Daniel J. Bauer, Patrick J. Curran, Maleeha Maroon, Department of Psychology and Neuroscience, University of North Carolina, Chapel Hill, NC 27599-3270, USA, hussong@unc.edu, dbauer@email.unc.edu, curran@unc.edu, maleeha@unc.edu Curt Beckwith, The Miriam Hospital, 164 Summit Ave, Providence, RI 02906, USA, CBeckwith@Lifespan.org Kevin Knight, Institute of Behavioral Research, Texas Christian University, Box 298740, Fort Worth, TX 76129 USA, k.knight@tcu.edu Jennifer Lorvick, RTI International, 351 California Street, Suite 500, San Francisco, CA 94014, USA, jlorvick@rti.org |
| ISSN: | 0376-8716 1879-0046 |
| DOI: | 10.1016/j.drugalcdep.2018.10.003 |