Forecasts in a slightly misspecified finite order var / Ulrich K. Müller, James H. Stock.

Author/creator Müller, Ulrich K.
Other author Stock, James H.
Other author National Bureau of Economic Research.
Format Electronic
Publication InfoCambridge, MA : National Bureau of Economic Research,
Supplemental ContentFull text available from NBER Working Papers

SeriesNBER working paper series ; working paper 16714
Working paper series (National Bureau of Economic Research : Online) ; working paper no. 16714. UNAUTHORIZED
Summary "We propose a Bayesian procedure for exploiting small, possibly long-lag linear predictability in the innovations of a finite order autoregression. We model the innovations as having a log-spectral density that is a continuous mean-zero Gaussian process of order 1/√T. This local embedding makes the problem asymptotically a normal-normal Bayes problem, resulting in closed-form solutions for the best forecast. When applied to data on 132 U.S. monthly macroeconomic time series, the method is found to improve upon autoregressive forecasts by an amount consistent with the theoretical and Monte Carlo calculations"--National Bureau of Economic Research web site.
General noteTitle from PDF file as viewed on 4/28/2011.
Bibliography noteIncludes bibliographical references.
Access restrictionAvailable only to authorized users.
Other formsAlso available in print.
Technical detailsMode of access: World Wide Web
Genre/formElectronic books.
LCCN 2011655940

Availability

Library Location Call Number Status Item Actions
Electronic Resources Access Content Online ✔ Available