March 2, 2015
This paper evaluates the performance of a variety of structural VAR models in estimating the impact of credit supply shocks. Using a Monte-Carlo experiment, we show that identification based on sign and quantity restrictions and via external instruments is effective in recovering the underlying shock. In contrast, identification based on recursive schemes and heteroscedasticity suffer from a number of biases. When applied to US data, the estimates from the best performing VAR models indicate, on average, that credit supply shocks that raise spreads by 10 basis points reduce GDP growth and inflation by 1% after one year. These shocks were important during the Great Recession, accounting for about half the decline in GDP growth.
J.E.L classification codes: C15, C32, E32
Keywords:Credit supply shocks, Proxy SVAR, Sign restrictions, Identification via heteroscedasticity, DSGE models