Analysis of geographical disparities in temporal trends of health outcomes using space-time joinpoint regression

► Time trends in prostate cancer late-stage diagnosis vary greatly among Florida counties. ► Filtering noise in cancer rate data using binomial kriging improves the quality of the joinpoint regression model. ► Geographical disparities were the most widespread when a new screening procedure was introduced in the early nineties. ► Combining cluster and boundary analysis creates spatially compact groups of counties with similar temporal trends.