The ordered logistic regression model in psychiatry: rising prevalence of dementia in old people's homes

Abstract

Ordered logistic regression is an extension of binary logistic regression, and is particularly well suited to the analysis of many psychiatric scores. Its use is demonstrated in a pair of linked cross-sectional surveys of dementia in residents of old people's homes, first to model the association of dementia with demographic characteristics, and then to explore possible reasons for a rise in the prevalence of dementia in the homes over a four-year period.