A Cluster Analysis Typology of Suicide in the United States Air Force
Abstract
Background. Suicide remains a significant public health problem in the United States (U.S.) military. Given the heterogeneity among suicide decedents, what remains unclear is whether subgroups, or typologies, exist that characterize suicide decedents and whether these typologies can be effectively targeted in preventing suicide. Purpose. A decade of surveillance data of U.S. Air Force (USAF) suicides was examined to determine whether a useful typological model of suicide could be constructed. Specific aims of the current study were (1) to describe the characteristics of USAF suicide decedents for the past decade; (2) to compare characteristics of USAF suicide decedents before the onset of Operation Enduring Freedom (OEF) with suicides occurring afterwards; (3) to employ hierarchical cluster analysis to determine the presence of subgroups based on demographic and psychosocial characteristics; and (4) to evaluate the stability and external validity of these subgroups. Method. Data on all USAF active duty suicides registered in the Suicide Event Surveillance System (SESS) database, between 1999 and 2009, were obtained from the USAF Suicide Prevention Program (USAFSPP). Preliminary analyses focused on general characteristics of suicide decedents and potential differences between pre- and post- OEF suicides. Next, hierarchical cluster analysis of demographic and psychosocial variables was used to assign all cases to initial clusters and determine cluster centroids. Iterative partitioning clustering procedures were employed to determine cluster stability via split-half analysis. Members of the observed clusters were compared on their utilization of helping services to assess external validity and usefulness of the cluster solution.
Document Details
- Document Type
- Technical Report
- Publication Date
- Aug 01, 2011
- Accession Number
- AD1013359
Entities
People
- Jeffery S. Martin
Organizations
- Uniformed Services University of the Health Sciences