Using leading indicators to forecast US home sales in a Bayesian vector autoregressive framework

This article uses Bayesian vector autoregressive models to examine the usef ulness of leading indicators in predicting U.S. home sales. The benchmark B ayesian model includes home sales, price of homes, mortgage rate, real pers onal disposable income, and unemployment rate. We evaluate the forecasting performance of six alternative leading indicators by adding each, in turn, to the benchmark model. Out-of-sample forecast performance over three perio ds shows that the model that includes building permits authorized consisten tly produces the most accurate forecasts. Thus, the intention to build in t he future provides good information with which to predict U.S. home sales. Another finding suggests that leading indicators with longer leads outperfo rm the short-leading indicators.