Concentration and persistence in the level of health expenditures over time and their prediction

Estimates of the health care expenses of the U.S. population are critical to policymakers concerned with access to medical care and the cost and sources of payment for that care. In 2006, health care expenses among the non-institutionalized population exceeded one trillion dollars. Medical care expenses, however, are highly concentrated among a relatively small proportion of individuals. Using detailed information from Medical Expenditure Panel Survey, estimates of both the concentration and the persistence in level of health care expenditures over time are presented. Studies that examine the persistence of high levels of expenditures over time are essential to help discern the factors most likely to drive health care spending and the characteristics of the individuals who incur them. This research effort assesses the performance of prediction models that attempt to discern those individuals most likely to experience persistently high levels of medical expenditures in the future from their counterparts. Given the high concentration of health care expenditures among a relatively small percentage of the population, a prediction model that can accurately identify the persistence of high levels of expenditures is an important analytical tool. This type of modeling effort also enhances the ability to discern the causes of high health care expenses and the characteristics of the individuals who incur them. The models that are presented have particular relevance as statistical tools to facilitate efficient sampling strategies that permit the selection of an over-sample of individuals likely to incur persistently high levels of medical expenditures in the future.