Federal Reserve Bank of Minneapolis Research Department Working Paper: Forecasting with Bayesian Vector Autoregressions—Five Years of Experience by Robert B. Litterman. This paper discusses the use of Bayesian Vector Autoregressions (BVAR) for economic forecasting. BVAR models are relatively simple and inexpensive to use, and they generate forecasts that are as accurate as some of the most expensive forecasts. BVAR has a distinct advantage over traditional econometric models in that it does not require judgmental adjustment, making it a scientific method that can be evaluated on its own. BVAR also generates a complete, multivariate probability distribution for future economic outcomes, which is more realistic than those generated by other approaches. The paper discusses the problem of economic forecasting, the justification for the Bayesian approach, its implementation, and the performance record of a small BVAR model used over the past five years. It also compares BVAR forecasts with those of other forecasting services and discusses the challenges of measuring forecast performance. The paper concludes that BVAR models provide accurate forecasts and are a valuable tool for economic forecasting.Federal Reserve Bank of Minneapolis Research Department Working Paper: Forecasting with Bayesian Vector Autoregressions—Five Years of Experience by Robert B. Litterman. This paper discusses the use of Bayesian Vector Autoregressions (BVAR) for economic forecasting. BVAR models are relatively simple and inexpensive to use, and they generate forecasts that are as accurate as some of the most expensive forecasts. BVAR has a distinct advantage over traditional econometric models in that it does not require judgmental adjustment, making it a scientific method that can be evaluated on its own. BVAR also generates a complete, multivariate probability distribution for future economic outcomes, which is more realistic than those generated by other approaches. The paper discusses the problem of economic forecasting, the justification for the Bayesian approach, its implementation, and the performance record of a small BVAR model used over the past five years. It also compares BVAR forecasts with those of other forecasting services and discusses the challenges of measuring forecast performance. The paper concludes that BVAR models provide accurate forecasts and are a valuable tool for economic forecasting.