Discriminant Function Analyses: Classifying Drugs/Violence Victimization Typologies Among Incarcerated Rural Women

This study examined the relationship between drug use and violence victimization among incarcerated women in Appalachian Kentucky. The purpose of this study was to test the utility of Goldstein's tripartite conceptual framework among rural incarcerated women, by examining whether distinct drugs/violence nexus groups could be classified based on psychopharmacological, economic-compulsive, and systemic factors. This study used secondary data from a National Institute on Drug Abuse (NIDA)-funded grant focused on risk reduction among high-risk incarcerated women in Appalachia (N = 400). Predicted drugs/violence groups were developed using a series of discriminant function analyses. The data yielded three statistically significant discriminant models. Findings of the classified groupings indicated support for three distinct drugs/violence victimization subgroups. The psychopharmacological group showed the greatest prevalence (n = 181; Wilks's λ = .389, F = 3.94, p < .001), followed by the economic-compulsive group (n = 77; Wilks's λ = .584, F = 11.86, p < .001) and systemic group (n = 55) significant (Wilks's λ = .994, F = 2.247, p < .035). To date, this is the first study to report a relationship between systemic violence victimization among rural communities. These findings could offer novel considerations for theory development and implications for clinical practice regarding the drug-related risks for violence victimization among rural incarcerated women.