State Correlation and Forecasting: A Bayesian Approach Using Unobserved Components Models
Implications for signal extraction from specifying unobserved components (UC) models with correlated or orthogonal innovations have been well investigated. In contrast, the forecasting implications of specifying UC models with different state correlation structures are less well understood. This paper attempts to address this gap in light of the recent resurgence of studies adopting UC models for forecasting purposes. Four correlation structures for errors are entertained: orthogonal, correlated, perfectly correlated innovations, and a new approach that combines features from two contrasting cases, namely, orthogonal and perfectly correlated innovations. Parameter space restrictions associated with different correlation structures and their connection with forecasting are discussed within a Bayesian framework. As perfectly correlated innovations reduce the covariance matrix rank, a Markov Chain Monte Carlo sampler, which builds upon properties of Toeplitz matrices and recent advances in precision-based algorithms, is developed. Our results for several measures of U.S. inflation indicate that the correlation structure between state variables has important implications for forecasting performance as well as estimates of trend inflation.