MODELLING INCOME PROCESSES WITH LOTSOF HETEROGENEITY

All empirical models of earnings processes in the literature assume agood deal of homogeneity. In contrast to this we model earnings processesallowing for lots of heterogeneity between agents. We also introduce an ex-tension to the linear ARMA model that allows that the initial convergenceto the long run may be di¤erent from that implied by the conventionalARMA model. This is particularly important for unit root tests which areactually tests of a composite of two independent hypotheses. We …t ourmodels to a variety of statistics including most of those considered by pre-vious investigators. We use a sample drawn from the PSID, and focus onwhite males with a high school degree. Despite this observable homogene-ity we …nd much greater latent heterogeneity than previous investigators....