Testing a DSGE model of the EU using indirect inference

We use the method of indirect inference, using the bootstrap, to test the Smets and Wouters model of the EU against a VAR auxiliary equation describing their data; the test is based on the Wald statistic. We find that their model generates excessive variance compared with the data. If the errors are scaled down, then the original model marginally passes the Wald test. We compare a New Classical version of the model which passes the test but generates a combination of excessive inflation variance and inadequate output variance. If the large consumption and investment errors are removed as possibly due to low frequency events, then the New Classical version passes easily while the original version is strongly rejected.