There is a concern that ordered responses on health questions may differ across populations or even across subgroups of a population. This reporting heterogeneity may invalidate group comparisons and measures of health inequality. This paper proposes a test for differential reporting in ordered response models which allows us to distinguish between cut-point shift and index shift. The method is illustrated using Canadian National Population Health Survey data. The McMaster Health Utility Index (HUI) is used as a more objective health measure than the simple 5-point scale of self-assessed health. We find clear evidence of index shifting and cut-point shifting for age and gender, but not for income, education or language.
hierarchical ordered probit health measurement cut-point shift index shift Canada