Modeling dynamics of metal price series via state space approach with two common factors

摘要

In this paper we model the dynamics of 100 years long monthly price series of eight non-ferrous and precious metals. Applying the state space framework we impose and identify two common factors related to non-ferrous and precious metals, respectively, which exhibit quite distinct autoregressive dynamics. The preferred two common factor specifications outperform single common factor approaches which are usually used in the current literature. Furthermore, we provide interpretation for the extracted common factors by investigating their exposure to the major macroeconomic fundamentals.