-
Views
-
Cite
Cite
Melissa A Lippold, Kirsten Kainz, Elaina Sabatine, Using Advanced Quantitative Methods to Study the Prevention of Social Problems, The British Journal of Social Work, Volume 47, Issue 8, December 2017, Pages 2238–2255, https://doi.org/10.1093/bjsw/bcw172
Close - Share Icon Share
Abstract
Social work has embraced prevention as one of its grand challenges—recognising the need to understand risk and protective factors for social problems that, if addressed, may prevent social disadvantage and mental health problems from occurring. To best study prevention, social workers must become fluent in understanding and using advanced methodologies that illuminate developmental processes, depict individual and subgroup differences, and rule out potential confounds so as to shed light on important risk and protective factors. The purpose of this article is to provide a simple introduction to four advanced methods: latent growth curves (LGM), mediation models, latent class/profile models and propensity score models. Latent growth curve models are helpful for understanding changes in the developmental course of a risk factor over time. Mediation models are useful tools for understanding how risk and protective factors may affect outcomes. Latent class and latent profile models allow researchers to understand how combinations of risk factors may be linked to youth outcomes. Propensity score models allow researchers to reduce the effects of selection bias on their estimates of the relationships between risk factors and outcomes. We discuss the research questions appropriate for each type of model, the type of data required, and the strengths and weaknesses of each approach. We also include suggestions for further reading.
