Identifying age-cohort-time effects, their curvature and interactions from polynomials : examples related to sickness absence

In the paper is considered identification of coefficients in equations explaining a continuous variable, say the number of sickness absence days of an individual per year, by cohort, time and age, subject to their definitional identity. Extensions of a linear equation to polynomials, including additive polynomials, are explored. The cohort+time=age identity makes the treatment of interactions important. If no interactions between the three variables are included, only the coefficients of the linear terms remain unidentified unless additional information is available. Illustrations using a large data set for individual long-term sickness absence in Norway are given. The sensitivity to the estimated marginal effects of cohort and age at the samplemean, as well as conclusions about the equations’ curvature, are illustrated. We find notable differences in this respect between linear and quadratic equations on the one hand and cubic and fourth-order polynomials on the other. -- age-cohort-time problem ; identification ; polynomial regression ; interaction ; age-cohort curvature ; panel data ; sickness absence