Latent variable mixture models to test for differential item functioning: a population-based analysis

BACKGROUND: Comparisons of population health status using self-report measures such as the SF-36 rest on the assumption that the measured items have a common interpretation across sub-groups. However, self-report measures may be sensitive to differential item functioning (DIF), which occurs when sub-groups with the same underlying health status have a different probability of item response. This study tested for DIF on the SF-36 physical functioning (PF) and mental health (MH) sub-scales in population-based data using latent variable mixture models (LVMMs). METHODS: Data were from the Canadian Multicentre Osteoporosis Study (CaMos), a prospective national cohort study. LVMMs were applied to the ten PF and five MH SF-36 items. A standard two-parameter graded response model with one latent class was compared to multi-class LVMMs. Multivariable logistic regression models with pseudo-class random draws characterized the latent classes on demographic and health variables. RESULTS: The CaMos cohort consisted of 9423 respondents. A three-class LVMM fit the PF sub-scale, with class proportions of 0.59, 0.24, and 0.17. For the MH sub-scale, a two-class model fit the data, with class proportions of 0.69 and 0.31. For PF items, the probabilities of reporting greater limitations were consistently higher in classes 2 and 3 than class 1. For MH items, respondents in class 2 reported more health problems than in class 1. Differences in item thresholds and factor loadings between one-class and multi-class models were observed for both sub-scales. Demographic and health variables were associated with class membership. CONCLUSIONS: This study revealed DIF in population-based SF-36 data; the results suggest that PF and MH sub-scale scores may not be comparable across sub-groups defined by demographic and health status variables, although effects were frequently small to moderate in size. Evaluation of DIF should be a routine step when analysing population-based self-report data to ensure valid comparisons amongst sub-groups.