Integrative Mortality Models for the Study of Aging, Health, and Longevity: Benefits of Combining Data
In a number of longitudinal studies, individual health and physiological/biological variables are repeatedly measured for a relatively large number of study subjects. Such data have good potential for evaluating properties of dynamic mechanisms involved in the regulation of aging-related changes, and their effects on health and survival outcomes. Often it happens that measurements of some important variables or health outcomes that are omitted in one dataset were measured in another dataset. In such cases, combining data would be a promising alternative for comprehensive analyses of mechanisms of aging-related changes, health decline, and life span. These analyses can be performed within a framework of one comprehensive model of human aging, health, and mortality. In this chapter, a method of statistical modeling for joint analyses of longitudinal data on aging, health, and longevity collected using different observational plans is described. The method is based on the mathematical model of human aging, health, and mortality described in Chap. 15. Observational plans corresponding to each dataset play a crucial role in specifying the likelihood functions of observed components of the data. The results of our analyses indicate that parameters of both continuous and jumping components of the model can be identified from the data.
