Using data from the U.S. Health and Retirement Study (HRS) and the English Longitudinal Study of Ageing (ELSA), we will estimate a stochastic process for the dementia incidence rate (the probability an individual will succumb to dementia each year) using methods that measure population trends with relatively small samples. By estimating time trends amid sampling uncertainty, we test whether estimated dementia trends represent population-level trends or mere sampling uncertainty. Forecasts from our study will be useful to inform future health care spending estimates. Furthermore, we will estimate the incidence rate by race, ethnicity, and gender. Minorities may show differences both in the time trends in and the level of dementia incidence, which our estimates will quantify.
