US tax and spending shocks 1950-2019 : SVAR overidentification with external instruments

An SVAR in US federal spending, federal revenue, and GDP is a standard setting for the study of the impact of fiscal shocks. An appealing feature of identifying a fiscal shock with an external instrument is that one can find the effects of that shock without fully identifying the SVAR. But we show that fully or almost fully instrumenting the SVAR allows one to overidentify the model by restricting the shock covariances to be zero. In this application the overidentifying restrictions are not rejected. Compared to the unrestricted case the restricted SVAR yields (a) greater precision in estimating impulse response functions and multipliers and (b) smaller estimated effects of government spending shocks on output growth.