This paper develops a forecasting procedure based on a Bayesian method for estimating vector autoregressions. The procedure is applied to ten macroeconomic variables and is shown to improve out-of-sample forecasts relative to univariate equations. The authors provide unconditional forecasts as of 1982:12 and 1983:3, and describe how such models can be used to make conditional projections and analyze policy alternatives. They also analyze a Congressional Budget Office (CBO) forecast made in 1982:12. While no automatic causal interpretations arise from these models, they provide a detailed characterization of the dynamic statistical interdependence of economic variables, which can help in evaluating causal hypotheses. The paper discusses the specification of the prior distribution, the forecasting procedure, and the results of the model's performance in forecasting and conditional projection. The authors conclude that the model captures significant cross-variable interactions and provides a more accurate forecast than univariate methods.This paper develops a forecasting procedure based on a Bayesian method for estimating vector autoregressions. The procedure is applied to ten macroeconomic variables and is shown to improve out-of-sample forecasts relative to univariate equations. The authors provide unconditional forecasts as of 1982:12 and 1983:3, and describe how such models can be used to make conditional projections and analyze policy alternatives. They also analyze a Congressional Budget Office (CBO) forecast made in 1982:12. While no automatic causal interpretations arise from these models, they provide a detailed characterization of the dynamic statistical interdependence of economic variables, which can help in evaluating causal hypotheses. The paper discusses the specification of the prior distribution, the forecasting procedure, and the results of the model's performance in forecasting and conditional projection. The authors conclude that the model captures significant cross-variable interactions and provides a more accurate forecast than univariate methods.