Abstract: This paper provides a famework for estimating parameters in a wide class of dynamic rational expectations models. The framework recognizes that RE models are often meant to match the data only in limited ways. In particular, interest may focus on a subset of frequencies. This paper designs a frequency domain version of GMM. The estimator has several advantages over traditional GMM. Aside from allowing band-restricted estimation, it does not require making arbitrary instrument or weighting matrix choices. The framework also includes least squares, maximum likelihood, and band restricted maximum likelihood as special cases.

Full paper (225 KB PDF) | Full paper (221 KB Postscript)