A dynamic principal components analysis based on multivariate matrix normal dynamic linear models

摘要

In this paper, we propose a multivariate dynamic linear model (MDLM) that allows us to carry out a dynamic principal components analysis in a set of multivariate time series and to analyse the similarity in their evolution once the influence of non-stationarity in each of them has been removed. In order to illustrate the methodology, we consider the distribution of value added of the firms operating in the Spanish Transport Material Manufacturing sector.