Jason Williams is a research psychologist in the Substance Use Prevention and Evaluation Research program. He has over 15 years of experience in developing, translating, and using advanced statistical methods in applied research. Much of Dr. Williams’s work has focused on evaluation of small- and large-scale substance use and violence prevention programs focusing on at-risk populations, especially children/adolescents and military personnel. He has served as analysis task lead and primary analyst and methodologist for multiple community and school-based evaluations such as the Start Strong dating violence prevention program, Safe Schools/Healthy Students program, the School Violence Prevention Program, and evaluations of mindfulness and mental health promotion interventions. He has also led analyses for several past iterations of the Department of Defense’s Survey of Health Related Behaviors in both the Active Duty and Reserve Components, evaluations of Basic Combat Training stress reduction and readiness promotion programs, and substance use prevention trials in the military.
In addition to program evaluation, Dr. Williams has worked extensively with studies examining child and youth development and the impact of risk and protective factors on important outcomes. He was an analysist for the Eunice Kennedy Shriver National Institute of Child Health and Human Development (NICHD) Study of Early Child Care and Youth Development (SECCYD) and has assisted with several National Survey of Child and Adolescent Well-Being (NSCAW) projects in the past. He is a collaborator with the National Institutes of Health (NIH) ECHO project, modeling the impact of early child experiences on later health outcomes and immune response. He is currently lead psychometrician for a U.S. Agency for International Development (USAID) project developing an international toolkit for the measurement of child experiences of gender-based violence and attitudes in the community, home, and school.
Dr. Williams has methodological expertise in mediation analysis, psychometrics, missing data techniques, bootstrapping, multilevel models, structural equation modeling, longitudinal growth models, and other latent variable models, such as factor analysis and latent class analysis.