Forecasting industrial employment figures in Southern California: A Bayesian vector autoregressive model

In this paper, we construct a Bayesian vector autoregressive model to forec ast the industrial employment figures of the Southern California economy. T he model includes both national and state variables. The root mean squared error (RMSE) and the Theil's U statistics are used in selecting the Bayesia n prior. The out-of-sample forecasts derived from each model and prediction of the turning points show that the Bayesian VAR model outperforms the ARI MA and the unrestricted VAR models. At longer horizons the BVAR model appea rs to do relatively better than alternative models. A prior that becomes in creasingly looser produces more accurate forecasts than a tighter prior in the BVAR estimations.