The aim of this study was to perform a psychometric analysis on the Geriatric Oral Health Assessment Index (GOHAI) using Rasch analysis, a modern statistical approach for examining rating scale data. Eighty-five subjects, long-term residents of a nursing home, were analysed using the GOHAI. The mean GOHAI score (range 0-48) was 11. Two of the five rating categories (1 = seldom; 3 = often) did not comply with the Rasch criteria for category functioning. After collapsing rating categories into a three-level rating scale (0 = never; 1 = sometimes; 2 = often/always), the new model met the set criteria. Item 12 'sensitivity to hot, cold or sweets' was misfitting. Rasch analysis showed both the unidimensionality of (at least) 11 of the 12 items of GOHAI, and the possibility of simplifying the structure of its rating scale.