The concept of Granger causality is an important tool in applied macroeconomics. Recursive econometric methods to analyze the temporal stability of Granger-causal relationships have recently been developed. These recursive procedures are used to re-evaluate the temporal stability of Granger causality between US industrial production and three macroeconomic variables. There appears to be significant evidence of temporal variation in the causal relationships. A clear pattern that emerges from the results is that the causal channels from all three variables to industrial production appear to be very strong in the latter part of the sample period.