Aggregating Rational Expectations Models in thePresence of Unobserved Micro Heterogeneity

Our paper addresses the correction of the aggregation bias in linear rational expectations modelswhen there is some unobserved micro-parameter heterogeneity and only macro data are available.Starting from Lewbel (1994), we propose two new consistent estimators, which rely on aexible parametric specication of the cross-sectional parameter distributions and account forthe dependence across coefficients inherent in such models. A Monte-Carlo study reveals thatthe nite-sample and asymptotic properties of the proposed estimators correct the aggregationbias found with the maximum-likelihood and generalized-method-of-moments approaches.[...]