Dynamic Window-level Granger Causality of Multi-channel Time Series
This work addresses the limitation of existing Granger causality methods for researchers and practitioners analyzing time series with dynamic causal relationships, though it is incremental as it builds on traditional methods with a novel indexing approach.
The paper tackles the problem of modeling dynamic causalities in multi-channel time series data, which traditional Granger causality methods cannot handle due to their assumption of constant causalities. It presents the dynamic window-level Granger causality method (DWGC) with a causality indexing trick, showing improved detection of window-level causalities on synthetic and real-world datasets.
Granger causality method analyzes the time series causalities without building a complex causality graph. However, the traditional Granger causality method assumes that the causalities lie between time series channels and remain constant, which cannot model the real-world time series data with dynamic causalities along the time series channels. In this paper, we present the dynamic window-level Granger causality method (DWGC) for multi-channel time series data. We build the causality model on the window-level by doing the F-test with the forecasting errors on the sliding windows. We propose the causality indexing trick in our DWGC method to reweight the original time series data. Essentially, the causality indexing is to decrease the auto-correlation and increase the cross-correlation causal effects, which improves the DWGC method. Theoretical analysis and experimental results on two synthetic and one real-world datasets show that the improved DWGC method with causality indexing better detects the window-level causalities.