We present a dynamic model of individuals’ educational investments that allows us to explore alternative modeling strategies for forecasting future wage distributions. The key innovation we propose is an approach to forecasting that relies only on the information that would be available at the actual time decisions are made and which incorporates the role of parameter uncertainty into the decision‐making process. We compare the performance of our method with alternative models of forecasting behavior, based on CPS data over the period 1964–2004.

In this paper, we expand on the seminal work of Altonji and Shakotko (1987) and Topel (1991) and reinvestigate the returns to seniority in the United States. We begin with the same wage equation as in previous studies. We extend the model of Hyslop (1999) and explicitly model the participation/employment and inter-firm mobility decisions, which, in turn, define the individual's experience and seniority. We introduce into the wage equation a summary of the workers' entire career path. The three-equation system is estimated simultaneously using data from the Panel Study of Income Dynamics (PSID). We find that for each of the three education groups studied the returns to seniority are larger than those previously found in the literature.