More than 50 years ago, Friedman and Schwartz examined historical data for the United States and found evidence of procyclical movements in the money stock, which led corresponding movements in output. We find similar correlations in more recent data; these appear most clearly when Divisia monetary aggregates are used in place of the Federal Reserve's official, simple‐sum measures. When we use information in Divisia money to estimate a structural vector autoregression, identified monetary policy shocks appear to have large and persistent effects on output and prices, with a lag that has lengthened considerably since the early 1980s.