Working Paper: CEPR ID: DP9655
Authors: Eric Ghysels; Jonathan B. Hill; Kaiji Motegi
Abstract: It is well known that temporal aggregation has adverse effects on Granger causality tests. Time series are often sampled at different frequencies. This is typically ignored, and data are merely aggregated to the common lowest frequency. We develop a set of Granger causality tests that explicitly take advantage of data sampled at different frequencies. We show that taking advantage of mixed frequency data allows us to better recover causal relationships when compared to the conventional common low frequency approach. We also show that the mixed frequency causality tests have higher local asymptotic power as well as more power in finite samples compared to conventional tests.
Keywords: Granger causality; mixed data sampling; MIDAS; temporal aggregation; vector autoregression (VAR)
JEL Codes: C12; C32
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| mixed frequency Granger causality tests (C22) | recover underlying causal relationships (C32) |
| mixed frequency Granger causality tests (C22) | outperform traditional methods (C52) |
| high frequency variables (C58) | affect low frequency variables (C22) |
| low frequency variables (C29) | affect high frequency variables (C22) |