Can people learn rational expectations? - An 'ecological' approach

In this note the stability of the rational expectations equilibrium for the Foster and Frierman (1990) version of the Blume and Easley (1982) model is investigated under the assumption that the learning mechanism used by economic agents is based on a selection mechanism on a class of competing models having a 'physical' meaning for the agent and not on the interpolation of models having no clear physical meaning, as it is often the case in the literature on learning rational expectations. It is found that, under the standard assumption that the rational expectations model is in the information set of the uninformed trader no matter his degree of rationality, convergence to it is less likely the higher the uninformed agent's degree of rationality, in a sense to be specified in the paper. Some comments on the result are also provided. © 1994 Springer-Verlag.