Loneliness in adolescence: a Rasch analysis of the Perth A-loneness scale.

Purpose The psychometric properties of the Perth A-loneness Scale (PALs) have been extensively validated using classical test theory, but to date no studies have applied a Rasch analysis. The purpose of this study was to validate the PALs four subscales, using Rasch analysis. Methods Responses from 1484 adolescents (58% female, mean age = 12.8 years), 131 of whom had a diagnosed neurodevelopmental disorder, from 10 Western Australian secondary schools were included in the Rasch analysis. Overall fit, individual item fit, local response dependence, dimensionality, operation of response categories, and differential item functioning (DIF) were examined. Results The Rasch analysis supported the factor structure of the PALs. A reasonable to high reliability was obtained for each of the subscales. Participants did not distinguish consistently between the higher categories 'very often' and 'always' on three of the subscales. No item showed Differential Item Functioning (DIF) for neurodevelopmental disorder status and age. One item on each of the Positive and Negative Attitude to Aloneness subscales showed DIF for gender. Conclusion The results support the interval scale measurement properties of the PALs and provide clinicians and researchers with a measure to assess adolescent loneliness, a construct strongly associated with a constellation of mental health problems.