Psychometric Properties of Connor-Davidson Resilience Scale in a Sample of Military Active Duty Service Members

• Activity Number: 470
• Type: Contributed
• Date/Time: Wednesday, August 6, 2014 : 8:30 AM to 10:20 AM
• Sponsor: Section on Statistics in Defense and National Security
• Author(s): Weimin Zhang*+ and Salvatore Libretto and Courtney Lee
• Companies: Samueli Institute and Samueli Institute and Samueli Institute
• Keywords: Rasch model ; Item response theory ; latent class analysis ; confirmatory factor analysis ; Connor-Davidson Resilience Scale ; Resilience

Abstract

The objective of the study is to assess the psychometric properties of the Connor-Davidson Resilience Scale (CD-RISC) in a sample of military active duty service members. The 25-item scale was administered to N = 539 active duty service members in treatment for Post-Traumatic Stress Disorder. In this set of analyses we try to explore relevant questions such as: Can items in the CD-RISC scale be used to find distinct types of resilience from item responses? If yes, what are the characteristics of those items? Can particular subtypes of related resilient types (latent classes) be found in the data? To what extent is the measurement of resilience consistent with the accepted definition of the concept? Whether the scale can demonstrate acceptable approximation to Rasch model requirements? Does the scale work equally well across different variables (e.g. age, military experience)? Does the scale discriminate the sample into enough levels of resilience to be meaningful? Data were explored and analyzed using structural equation modeling latent class analysis methods, factor analysis, linear and nonlinear regression models and item response theory Rasch model approach.