A set of rigorous diagnostic techniques is used to evaluate the forecasting performance of five multivariate time-series models for the U.S. cattle sector. The root-meansquared-error criterion along with an evaluation of the rankings of forecast errors reveals that the Bayesian vector autoregression (BVAR) and the unrestricted VAR (UVAR) models generate forecasts which are superior to both a re...

The predictive likelihood is useful for ranking models in forecast comparison exercises using Bayesian inference. We discuss how it can be estimated, by means of marginalization, for any subset of the observables in linear Gaussian state-space models. We compare macroeconomic density forecasts for the euro area of a DSGE model to those of a DSGE-VAR, a BVAR, and a multivariate random walk over ...

There is increasing interest in detecting collective anomalies: potentially short periods of time where the features data change before reverting back to normal behaviour. We propose a new method for anomaly VAR models. Our focus on situations coefficient matrix at an sparse, i.e. small number entries change. To tackle this problem, we test statistic local segment that built lasso estimator mod...