Reconciled Estimates of Monthly GDP in the US*

In the US, income and expenditure-side estimates of GDP (GDPI GDPE) measure "true" with error are available at a quarterly frequency. Methods exist for using these proxies to produce reconciled true GDP. this paper, we extend methods provide historical monthly We do Bayesian mixed frequency vector autoregression (MF-VAR) involving GDPE, GDPI, unobserved GDP, indicators short-term economic activity. Our MF-VAR imposes restrictions that reflect measurement-error perspective (that is, two assumed equal plus measurement error). Without further restrictions, our model is unidentified. consider range allow point set identification show they lead informative estimates. illustrate how new data contribute understanding business cycles real-time application nowcasting over pandemic recession.