Showing 1 - 10 of 264
We propose methods for testing hypothesis of non-causality at various horizons, as defined in Dufour and Renault (1998, Econometrica). We study in detail the case of VAR models and we propose linear methods based on running vector autoregressions at different horizons. While the hypotheses...
Persistent link: https://www.econbiz.de/10005100843
Résumé: Nous étudions la puissance en terme de prévision des processus basés sur la méthode du noyau en utilisant la version non paramétrique du critère « Final Prediction error » pour identifier un processus fonctionnel hétéroscédastique. Cette identification nécessite une...
Persistent link: https://www.econbiz.de/10015255070
Résumé: Nous étudions la puissance en terme de prévision des processus basés sur la méthode du noyau en utilisant la version non paramétrique du critère « Final Prediction error » pour identifier un processus fonctionnel hétéroscédastique. Cette identification nécessite une...
Persistent link: https://www.econbiz.de/10015255088
The forecasting literature has identified three important and broad issues: the predictive content is unstable over time, in-sample and out-of-sample discordant results and the problematic statistical inference with highly persistent predictors. In this paper, we simultaneously address these...
Persistent link: https://www.econbiz.de/10009421811
The main objective of this study is to look for the best model for forecasting inflation rate and real growth for each CEMAC country. Using AR, VAR and BVAR models, it is clear from our study that forecasts made from Bayesian models have a higher predictive power than those made by classical...
Persistent link: https://www.econbiz.de/10015269552
This paper proposes an indirect inference (Gourieroux, Monfort and Renault, 1993; Smith, 1993) estimation method for a large class of dynamic equilibrium models. Our approach is based on the observation that the econometric structure of these systems naturally generates auxiliary equilibria that can...
Persistent link: https://www.econbiz.de/10010499879
Statistical tests in vector autoregressive (VAR) models are typically based on large-sample approximations, involving the use of asymptotic distributions or bootstrap techniques. After documenting that such methods can be very misleading even with fairly large samples, especially when the number...
Persistent link: https://www.econbiz.de/10005100698
We estimate the reaction function of monetary policy in the Euro area and derive the Taylor-type policy rule that a would-be ECB would have followed since the beginning of the European Monetary System (1979-2003). We first follow the standard GMM methodology developed by Clarida, Galí and...
Persistent link: https://www.econbiz.de/10005056522
Summary: The European Union absorbs nearly 75% of Tunisian exports and represents about 50% of Tunisian imports, which explains the important weight of the euro in the Tunisian dinar anchor basket. Thus, the purpose of this article is to predict short-term exchange rate fluctuations EUR/TND,...
Persistent link: https://www.econbiz.de/10015258910
In this paper, we study the asymptotic distribution of a simple two-stage (Hannan-Rissanen-type) linear estimator for stationary invertible vector autoregressive moving average (VARMA) models in the echelon form representation. General conditions for consistency and asymptotic normality are...
Persistent link: https://www.econbiz.de/10005100706