Modelos estructurales en el contexto de las series temporales

Resumo

Establishing the "stylised facts" associated with a set of time series is widely considered a crucial step in macroeconomic analysis. This is one of the reasons for wishing to model time series. For such models to be useful, they should be consistent with the stochastic properties of the data and present meaningful information. The structural time series models provide a useful framework with which to present stylised facts on time series and they are explicitly based on the stochastic properties of the data. The goal of this paper is to show the rationale underlying the structural time series models, the way in which univariate and multivariate models can be formulated and the way in which the structural methodology contrasts with ARIMA approach.