Psychometric Properties of the Unidimensional Relationship Closeness Scale based on classical test theory and Item response theory

A fundamental dimension along which all social and personal relationships vary is closeness. The purpose of present study was to investigate the factor structure and Item-Response parameters of the Unidimensional Relationship Closeness Scale. In a descriptive-correlational design and test validation 180 Birjand University students in the first study and 250 students in the second study were selected through multi-stage random sampling and completed the Unidimensional Relationship Closeness Scale (Dibel, Levin & Park, 2012). The data were analyzed by internal consistency, exploratory and confirmatory factor analysis, discrimination and threshold parameters and Item and test information curves. Results showed that the Unidimensional Relationship Closeness scale had a one-factor structure with explained variance of 63.39. Confirmatory factor validity was also confirmed. Cronbach's alpha coefficients were 0.95 and 0.93 and split half coefficients were 0.89 and 0.88, respectively in two studies. The Item-Response parameters were also at the optimum level. It seems that the Unidimensional Relationship Closeness scale, and in particular the structure of its 12 item versions, has a good reliability and validity in students.