Fractional Bayesian lag length inference in multivariate autoregressive processes
The multivariate autoregression, also known as the vector autoregression (VAR) model, has become the most widely used model for multiple time series and serves as a base for more complex models such as cointegration models. The first, and perhaps most difficult, problem in using VAR models is confronted with the choice of the number of lags in the model. Using a Bayesian approach the posterior distribution of the number of lags in the multivariate autoregression is derived under an improper prior for the model parameters. The fractional Bayes approach is used to handle the indeterminacy in the model selection caused by the improper prior. An asymptotic equivalence between the fractional approach and the Schwarz' Bayesian criterion is proved. Several priors and three loss functions are entertained in a simulation study which focuses on the choice of lag length. The fractional Bayes approach performs very well compared to the three most widely used information criteria, and is reasonable robust to changes in the prior distribution for the lag length, especially under the zero-one loss.
- A note on a Bayesian order determination procedure for vectorautoregressive processes
- A Bayesian estimation of lag lengths in distributed lag models
- Selection in VAR-models using equal and unequal lag-length procedures
- Optimal lag-length choice in stable and unstable VAR models under situations of homoscedasticity and ARCH
- Lag length and mean break in stationary VAR models
- Bayesian learning of graphical vector autoregressions with unequal lag-lengths
- A note on a Bayesian order determination procedure for vectorautoregressive processes
- Prior distributions for objective Bayesian analysis
- Structural learning of contemporaneous dependencies in graphical VAR models
- A Bayesian Approach to Modelling Graphical Vector Autoregressions
- Bayesian assessment of dimensionality in reduced rank regression
- BAYESIAN REFERENCE ANALYSIS OF COINTEGRATION
- A Bayesian estimation of lag lengths in distributed lag models
- Optimized multivariate lag structure selection
- Bayesian prior modeling in vector autoregressions via the Yule-Walker equations
This page was built for publication: Fractional Bayesian lag length inference in multivariate autoregressive processes
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2722252)
