Estimation of Heterogeneous Agent Models: A Likelihood Approach

Using a Bewley-Hugget-Aiyagari model we show how to use the Fokker-Planck equation for likelihood inference in heterogeneous agent (HA) models. We study finite sample properties of maximum estimator (MLE) Monte Carlo experiments using cross-sectional data on wealth and income. Kullback–Leibler divergence investigate identification problems that may affect inference. Unrestricted MLE leads considerable biases some parameters. Calibrating weakly identified parameters is shown be useful pin down remaining structural illustrate our approach by estimating US economy Survey Consumer Finances.