Generalizing the Bayesian Vector Autoregression Approach for Regional Interindustry Employment Forecasting
以美国佐治亚州数据为例，将贝叶斯向量自回归方法推广到区域间产业就业预测，通过引入区域投入产出系数和最终需求效应，改进了传统模型，并比较了不同模型的预测效果。
The Bayesian vector autoregression (BVAR) employment-forecasting approach is generalized using data for the state of Georgia. This study advances previous regional BVAR approaches by (a) incorporating regional input-output coefficients instead of national coefficients, (b) using the coefficients both to specify the prior means in one model and to weight the variances of a Minnesota-type prior in a second model, and (c) including final-demand effects and links to national and world economies. Out-of-sample forecasts produced by the generalized BVAR models are compared to forecasts produced from an autoregressive model, an unconstrained VAR model, and a Minnesota BVAR model.