Multidimensional item response theory to assess psychometric properties of GHQ-12 in parents of school children

• Published in: Journal of biostatistics and epidemiology Vol. 8; no. 1
• Main Authors: Haem, Elham, Doostfatemeh, Marziyeh
• Format: Journal Article
• Language: English
• Published: Tehran University of Medical Sciences 29.08.2022
• Subjects: general health questionnaire; Multidimensional item response theory; psychological distress; psychometrics properties
• ISSN: 2383-4196; 2383-420X
• DOI: 10.18502/jbe.v8i1.10405

Introduction: The multidimensional item response theory (MIRT) model provides an ideal foundation for assessing the psychological properties of a questionnaire designed with multidimensional structure. This study aimed to present the first use of MIRT models to investigate the psychometric properties of general health questionnaire (GHQ-12) in parents of school-aged children. Methods: A total of 1104 parents of school children-aged completed the Persian version of GHQ-12 questionnaire. One-dimensional IRT model and MIRT models with two and three factors were used to model the observed scores for each of the GHQ-12 items as a function of the subject's latent characteristics to consider the correlation between the dimensions of the questionnaire. Goodness of fit indices were reported for the three models, and the fits of items were assessed for the best model. Individual items were described in detail through item characteristic curves, and the amount of information carried by different items was presented using information curves. Results: The MIRT analysis with three factors corresponding with anxiety depression, social dysfunction and loss of confidence provided the best account of the GHQ-12 data. The model showed that all items were fitted adequately. Items varied in their discrimination ranged from 0.94 to 2.13, 1.31 to 2.74, and 2.87 to 3.57 for social dysfunction, anxiety depression, and loss of confidence, respectively. Moreover, items 8 and 2 provided the least information in social dysfunction and anxiety depression dimensions, respectively. Items in the loss of confidence dimension carried the most information among all items of the GHQ-12. Conclusion: The developed framework for evaluating the psychometric properties of GHQ-12 can be a suitable alternative to traditional approaches as well as unidimensional IRT models, the use of which has been restricted due to the multidimensional structure of the questionnaire.