Victor Fabrizzio Paliza Olivares, Edwin Salas-Blas, Mirian Pilar Grimaldo Muchotrigo, Jossué Correa-Rojas, Edson Jorge Huaire Inacio, Anthony Copez-Lonzoy
This study examines the psychometric properties and measurement invariance of the SELSA-S across sex and age in adults. The participants included 621 Peruvian adults with a mean age of 34 years (SD = 13.5) who completed the 15-item SELSA-S. Four models previously reported in the literature were examined via confirmatory factor analysis (CFA). Measurement invariance across sex and age was tested through multigroup CFA, whereas reliability was assessed via alpha, omega, and composite reliability coefficients. The results showed that the 12-item model had the best overall fit and factor stability in this sample (CFI = .974; TLI = .966; SRMR = .045). Measurement invariance across sex and age was supported, with negligible changes in model fit (Δ < .001). Reliability estimates for the 12-item model were optimal (ω, α, and ρc > .80). These findings support the use of the SELSA-S-12 as a reliable instrument for assessing loneliness in adults.