Autori: Maravall, Augustin, Mathis, Alexandre
Titolo: Encompassing univariate models in multivariate time series: a case study
Periodico: European University Institute of Badia Fiesolana (Fi). Department of Economics - Working papers
Anno: 1992 - Fascicolo: 88 - Pagina iniziale: 1992 - Pagina finale: 88

Through the encompassing principle, univariate ARIMA analysis could provide an important tool for diagnosis of VAR models: The univariate ARIMA models implied by the VAR should explain the results from univariate analysis. This comparison is seldom performed, possibly due to the paradox that, while the implied ARIMA models typically contain a large number of parameters, univariate analysis yields highly parsimonious models. Using a VAR application to six French macroeconomic variables, it is seen how the encompassing check is straightforward to perform, and surprisingly accurate. The VAR model explains univariate analysis, and the gain from multivariate modelling can be properly attributed to relationships among the variables. Finally, the univariate and VAR models are used to measure the persistence (or long-term effect) of shocks on the macro variables considered. Again, inferences based on univariate models are encompassed by the VAR, although, on occasion, inference based on univariate analysis can be misleading.




Testo completo: http://hdl.handle.net/1814/439

Esportazione dati in Refworks (solo per utenti abilitati)