Studies since the late 1970s have shown how differential rates of mortality for members of a birth cohort can produce an aggregate mortality rate pattern that looks nothing like the patterns of any of its members. In short, as frailer members of a cohort die off, the aggregate mortality rate converges toward the rates of the more robust members remaining alive in the cohort. Another consequence of this selection process is that the composition of characteristics that influence survival---i.e., indicators of frailty---change across the life course of the cohort as well. This process wreaks havoc on determining patterns of life course processes, like the shape of the relationship between socioeconomic status and health across age. Here I show that changing cohort composition can be useful for estimating the influence of fixed covariates on survival using cross-sectional data. I develop the method, test it via simulation, demonstrate it on sample data from the General Social Survey, and show how the method may be useful for dealing with the problems mortality selection presents in life course analyses.
