Psychometric Properties of the Chinese Version of the Comprehensive Autistic Trait Inventory

Background: The Comprehensive Autistic Trait Inventory (CATI) was an appropriate assessment tool that included all the principal dimensions related to autism defined in DSM-5 for the general population. However, its validity and reliability in the general Chinese population still need to be examined. Purpose: We revised the inventory and estimated the validity and reliability of the Chinese version of the CATI among 2232 general undergraduates. Methods: The Chinese version of the CATI (CATI-C) was administered to 2259 undergraduates using the online Questionnaires Star electronic system. Internal consistency, convergent validity, discriminant validity, test-retest reliability, and measurement invariance across gender were calculated. In order to determine the diagnostic accuracy and optimal cut-off score of the CATI-C, an analysis using the Receiver Operating Characteristic (ROC) was performed. Results: The CATI-C includes 35 items of two factors and six dimensions. CFA demonstrated that the fit index of the structure of the scale was good (Satorra-Bentler chi-square/degrees of freedom [S-B chi(2) /df] = 2.406, Standardized Root Mean Square Residual [SRMR] = 0.038, Root Mean Square Error of Approximation [RMSEA] = 0.037, Comparative Fit Index [CFI] = 0.929, Tucker-Lewis Index [TLI] = 0.917). The convergent validity examined based on the Autism Spectrum Quotient total score was satisfactory (r = 0.54). The internal consistency reliability of social factor, non-social factor, and total scores were 0.87, 0.85, and 0.90. The test-retest reliability was 0.80. A cut-off score of 115 provided optimal sensitivity and specificity for the CATI-C (sensitivity = 0.926, specificity = 0.781, and Youden's index = 0.707). Conclusion: The CATI-C has satisfactory reliability and validity in measuring autistic traits. It showed a good model fit for social and non-social second-order bifactors and measurement invariance across gender.