Using Rasch Analysis to Validate the Revised PSQI to Assess Sleep Disorders in Taiwan’s Hi-tech Workers

• Published in: Community mental health journal 2008-12, Vol.44 (6), p.417-425
• Main Authors: Chien, Tsair-Wei, Hsu, Sen-Yen, Tai, Chein, Guo, How-Ran, Su, Shih-Bin
• Format: Article
• Language: English
• Subjects: Adult; Biological and medical sciences; Community and Environmental Psychology; Discriminant analysis; Employees; Employment; Female; High tech industries; Humans; Insomnia; Investigations; Male; Medical sciences; Medicine; Medicine & Public Health; Older people; Original Paper; Psychiatry; Psychological tests; Psychology. Psychoanalysis. Psychiatry; Psychometrics - instrumentation; Psychometrics. Diagnostic aid systems; Psychopathology. Psychiatry; Quality assessment; Rasch model; Reproducibility of Results; Scale models; Scales; Science; Severity of Illness Index; Sleep; Sleep disorders; Sleep Wake Disorders - drug therapy; Sleep Wake Disorders - physiopathology; Surveys and Questionnaires - standards; Taiwan; Techniques and methods; Technology; Validity studies; Young Adult
• ISSN: 0010-3853; 1573-2789
• DOI: 10.1007/s10597-008-9144-9

The Pittsburgh Sleep Quality Index (PSQI) is an effective instrument for measuring the quality of sleep in older adults. In this study, we used Rasch analysis to validate the items of the revised PSQI (SC_PSQI) that contribute to a single construct. A total of 3,742 workers agreed to participate in this study. Both the appropriateness of the scoring rubrics and the unidimensionality of the SC_PSQI scale were investigated. All nine items fit the model’s expectations rather well. These results indicate that the SC_PSQI with a 0 to 2 scoring scale can be used as a unidimensionality to assess sleep quality.