Twenty Years of Time Series – Econometrics in Ten Pictures. James Stock, Spring 2017, Paper, “Twenty years ago, empirical macroeconomists shared some common understandings. One was that a dynamic causal effect—for example, the effect on output growth of the Federal Reserve increasing the federal funds rate—is properly conceived as the effect of a shock, that is, of an unanticipated autonomous change linked to a specific source. Following Sims (1980), the use of vector autoregressions to estimate the dynamic causal effect of shocks on economic variables was widespread.Link