National University of Singapore

The Effects of Temporal Aggregation on Granger Causality

Email address: artp9449@nus.edu.sg

Abstract:
Economists often have to use temporally aggregated data in causality tests. A number of theoretical studies have pointed out that temporal aggregation has distorting effects on causal inference. This paper examines the issue in detail by plugging in theoretical cross covariances into the limiting values of least squares estimates. An extensive Monte Carlo study is also conducted. It is observed that most distorting causal inferences are very likely at low levels of aggregation where the order of aggregation just exceeds the actual causal lag. At high levels of aggregation, causal information concentrates in contemporaneous correlations. At present, a data-based approach is not available to establish the direction of causality between contemporaneously correlated variables.

PDF file of paper: gulasekaran.pdf

Session: Topics in Time Series

Time: Sunday, 8 July, 8am - 9:30am

Room: B