James P Hughes1, Danielle F Haley2, Paula M Frew3, Carol E Golin4, Adaora A Adimora4, Irene Kuo5, Jessica Justman6, Lydia Soto-Torres7, Jing Wang8, Sally Hodder9. 1. Department of Biostatistics, University of Washington, Seattle, WA; Fred Hutchinson Cancer Research Center, Seattle, WA. Electronic address: jphughes@uw.edu. 2. Department of Behavioral Sciences and Health Education, Emory University Rollins School of Public Health, Atlanta, GA; Family Health International-FHI360, Durham, NC. 3. Department of Behavioral Sciences and Health Education, Emory University Rollins School of Public Health, Atlanta, GA; Department of Medicine, Division of Infectious Diseases, Emory University School of Medicine, Atlanta, GA. 4. School of Medicine, University of North Carolina, Chapel Hill, NC; Gillings School of Public Health, University of North Carolina, Chapel Hill, NC. 5. Department of Epidemiology and Biostatistics, George Washington University, Washington, DC. 6. Departments of Epidemiology and Medicine, ICAP at Columbia, Columbia University, New York, NY. 7. National Institute of Allergy and Infectious Diseases, Bethesda, MD. 8. Fred Hutchinson Cancer Research Center, Seattle, WA. 9. West Virginia University Clinical and Translational Science Institute, Morgantown, WV.
Abstract
PURPOSE: Reductions in risk behaviors are common following enrollment in human immunodeficiency virus (HIV) prevention studies. We develop methods to quantify the proportion of change in risk behaviors that can be attributed to regression to the mean versus study participation and other factors. METHODS: A novel model that incorporates both regression to the mean and study participation effects is developed for binary measures. The model is used to estimate the proportion of change in the prevalence of "unprotected sex in the past 6 months" that can be attributed to study participation versus regression to the mean in a longitudinal cohort of women at risk for HIV infection who were recruited from ten U.S. communities with high rates of HIV and poverty. HIV risk behaviors were evaluated using audio computer-assisted self-interviews at baseline and every 6 months for up to 12 months. RESULTS: The prevalence of "unprotected sex in the past 6 months" declined from 96% at baseline to 77% at 12 months. However, this change could be almost completely explained by regression to the mean. CONCLUSIONS: Analyses that examine changes over time in cohorts selected for high- or low- risk behaviors should account for regression to the mean effects.
PURPOSE: Reductions in risk behaviors are common following enrollment in human immunodeficiency virus (HIV) prevention studies. We develop methods to quantify the proportion of change in risk behaviors that can be attributed to regression to the mean versus study participation and other factors. METHODS: A novel model that incorporates both regression to the mean and study participation effects is developed for binary measures. The model is used to estimate the proportion of change in the prevalence of "unprotected sex in the past 6 months" that can be attributed to study participation versus regression to the mean in a longitudinal cohort of women at risk for HIV infection who were recruited from ten U.S. communities with high rates of HIV and poverty. HIV risk behaviors were evaluated using audio computer-assisted self-interviews at baseline and every 6 months for up to 12 months. RESULTS: The prevalence of "unprotected sex in the past 6 months" declined from 96% at baseline to 77% at 12 months. However, this change could be almost completely explained by regression to the mean. CONCLUSIONS: Analyses that examine changes over time in cohorts selected for high- or low- risk behaviors should account for regression to the mean effects.
Authors: Sally L Hodder; Jessica Justman; James P Hughes; Jing Wang; Danielle F Haley; Adaora A Adimora; Carlos Del Rio; Carol E Golin; Irene Kuo; Anne Rompalo; Lydia Soto-Torres; Sharon B Mannheimer; Letanya Johnson-Lewis; Susan H Eshleman; Wafaa M El-Sadr Journal: Ann Intern Med Date: 2013-01-01 Impact factor: 25.391
Authors: Danielle F Haley; Jonathan Lucas; Carol E Golin; Jing Wang; James P Hughes; Lynda Emel; Wafaa El-Sadr; Paula M Frew; Jessica Justman; Adaora A Adimora; Christopher Chauncey Watson; Sharon Mannheimer; Anne Rompalo; Lydia Soto-Torres; Zandraetta Tims-Cook; Yvonne Carter; Sally L Hodder Journal: AIDS Patient Care STDS Date: 2014-04 Impact factor: 5.078
Authors: Rob McCarney; James Warner; Steve Iliffe; Robbert van Haselen; Mark Griffin; Peter Fisher Journal: BMC Med Res Methodol Date: 2007-07-03 Impact factor: 4.615
Authors: Yu Liu; Sten H Vermund; Yuhua Ruan; Hongjie Liu; K Rivet Amico; Jane M Simoni; Bryan E Shepherd; Yiming Shao; Han-Zhu Qian Journal: J Int AIDS Soc Date: 2018-02 Impact factor: 5.396
Authors: Nina T Harawa; Heather Guentzel-Frank; William Jason McCuller; John K Williams; Gregorio Millet; Lisa Belcher; Heather A Joseph; Ricky N Bluthenthal Journal: J Urban Health Date: 2018-04 Impact factor: 5.801
Authors: Steven A Safren; James P Hughes; Matthew J Mimiaga; Ayana T Moore; Ruth Khalili Friedman; Kriengkrai Srithanaviboonchai; Mohammed Limbada; Brian D Williamson; Vanessa Elharrar; Vanessa Cummings; Jessica F Magidson; Charlotte A Gaydos; David D Celentano; Kenneth H Mayer Journal: J Int AIDS Soc Date: 2016-09-28 Impact factor: 5.396
Authors: Moses J E Flash; Wendy H Garland; Emily B Martey; Bruce R Schackman; Sona Oksuzyan; Justine A Scott; Philip J Jeng; Marisol Rubio; Elena Losina; Kenneth A Freedberg; Sonali P Kulkarni; Emily P Hyle Journal: Open Forum Infect Dis Date: 2019-12-16 Impact factor: 3.835