Abstract
This paper presents an extension of the Zellner-Palm methodology using the multiple time series representation of an underlying structural econometric model. The multiple time series approach avoids the problem of cancellation of common factors that has made it difficult to infer structural model characteristics from univariate time series models. In addition the correspondence between the structural model and the multiple time series model provides structural content to the tests for Granger-causality. The approach is illustrated with applications to small macroeconomic models of Friedman and Sargent and Wallace.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have