An Information Theory Approach to the Aggregation of Log-Linear Models

In this paper, an unrestricted aggregation method for heterogeneous log-linear functions is presented. It employs inequality measures derived from information theory in the construction of an exact representation of the aggregate behavior of the economy. A condition for the identification of average micro parameters is proposed. It is shown that the method leads to previous results in the field when adequate restrictions are imposed. Two macroeconomic applications are discussed: the aggregation of the Lucas supply function and the time-inconsistent behavior of an egalitarian social planner facing agents with heterogeneous discount rates.