No abstract

No abstract

Despite the commonly held belief that aggregate data display short-run comovement, there has been little discussion about the econometric consequences of this feature of the data. We use exhaustive Monte-Carlo simulations to investigate the importance of restrictions implied * Acknowledgments: This paper was written while João Victor Issler was visiting Monash University, and it was revised while Farshid Vahid was visiting Getulio Vargas Foundation. The hospitality of both institutions are gratefully acknowledged. We have beneÞted from comments and suggestions of Heather Anderson, Carlos Martins-Filho, Aman Ullah, Arnold Zellner (Editor), the Associate Editor, four anonymous referees, and participants of the Latin American and the European Meetings of the Econometric Society. We thank George Athanasopoulos for excellent research assistance. The authors are responsible for any remaining errors in this paper. João Victor Issler acknowledges the support of CNPq-Brazil and PRONEX. Farshid Vahid is grateful for Þnancial support provided by the Monash University Research Fund Grant No. 22.097.007, and CNPq-Brazil. † Corresponding author. by common-cyclical features for estimates and forecasts based on vector autoregressive models. First, we show that the "best" empirical model developed without common cycle restrictions need not nest the "best" model developed with those restrictions. This is due to possible differences in the lag-lengths chosen by model selection criteria for the two alternative models. Second, we show that the costs of ignoring common cyclical features in vector autoregressive modelling can be high, both in terms of forecast accuracy and efficient estimation of variance decomposition coefficients. Third, we Þnd that the Hannan-Quinn criterion performs best among model selection criteria in simultaneously selecting the lag-length and rank of vector autoregressions.

Using the generalized method of moments, we estimate structural parame ters related to relative-risk aversion, the discount rate of future utility, and the intertemporal elasticity of substitution in consumption for the Brazilian economy. Estimates are provided for three types of utility fun ction based on the consump tion capital asset pricing model: constant relative risk aversion utility, utility with external habit, and Kreps-Porteus utility. These results are analyzed and then compared to previous results using Brazilian and U.S. data. Moreover, we per form over-identifying restrictions tests of all estimated models to investigate the possible existence of the equity premium puzzle in Brazil. The overall results show that Brazilian consumers have a relatively high discount rate, a low intertemporal elasticity of substitution, and a high relative risk aversion coefficient. Also, there is no evidence of the existence of the equity premium puzzle in Brazil. .. This article is a revised version of Natalia S. Piqueira's Masters Thesis, done under the supervision of Joao Victor Issier. We thank Marco Antonio Bonomo, Rene Garcia, Ajax Moreira, an anonymous referee and Carlos Martins Filho (Editor) for their suggestions on an earlier version of this article. All the remaining errors are ours. We also thank CNPq and PRONEX for their financial support.

a b s t r a c tWe study the joint determination of the lag length, the dimension of the cointegrating space and the rank of the matrix of short-run parameters of a vector autoregressive (VAR) model using model selection criteria. We suggest a new two-step model selection procedure which is a hybrid of traditional criteria and criteria with data-dependant penalties and we prove its consistency. A Monte Carlo study explores the finite sample performance of this procedure and evaluates the forecasting accuracy of models selected by this procedure. Two empirical applications confirm the usefulness of the model selection procedure proposed here for forecasting.