TY - GEN
T1 - Discovery of causal time intervals
AU - Li, Zhenhui
AU - Zheng, Guanjie
AU - Agarwal, Amal
AU - Xue, Lingzhou
AU - Lauvaux, Thomas
N1 - Funding Information:
The work was funded from a gift to Penn State for the Pennsylvania State University General Electric Fund for the Center for Collaborative Research on Intelligent Natural Gas Supply Systems and was supported in part by NSF awards #1639150, #1618448, and #1544455. Lingzhou Xue’s research is supported by the American Mathematical Society Simons Travel Grant and NSF award #1505256. The views and conclusions contained in this paper are those of the authors and should not be interpreted as representing any funding agencies. References [1] J. Aaltonen and R. Östermark. A rolling test of granger causality between the finnish and japanese security markets. Omega, 25(6):635–642, 1997.
Publisher Copyright:
Copyright © by SIAM.
PY - 2017
Y1 - 2017
N2 - Causality analysis, beyond "mere" correlations, has become increasingly important for scientific discoveries and policy decisions. Many of these real-world applications involve time series data. A key observation is that the causality between time series could vary significantly over time. For example, a rain could cause severe traffic jams during the rush hours, but has little impact on the traffic at midnight. However, previous studies mostly look at the whole time series when determining the causal relationship between them. Instead, we propose to detect the partial time intervals with causality. As it is time consuming to enumerate all time intervals and test causality for each interval, we further propose an efficient algorithm that can avoid unnecessary computations based on the bounds of F-test in the Granger causality test. We use both synthetic datasets and real datasets to demonstrate the efficiency of our pruning techniques and that our method can effectively discover interesting causal intervals in the time series data.
AB - Causality analysis, beyond "mere" correlations, has become increasingly important for scientific discoveries and policy decisions. Many of these real-world applications involve time series data. A key observation is that the causality between time series could vary significantly over time. For example, a rain could cause severe traffic jams during the rush hours, but has little impact on the traffic at midnight. However, previous studies mostly look at the whole time series when determining the causal relationship between them. Instead, we propose to detect the partial time intervals with causality. As it is time consuming to enumerate all time intervals and test causality for each interval, we further propose an efficient algorithm that can avoid unnecessary computations based on the bounds of F-test in the Granger causality test. We use both synthetic datasets and real datasets to demonstrate the efficiency of our pruning techniques and that our method can effectively discover interesting causal intervals in the time series data.
UR - http://www.scopus.com/inward/record.url?scp=85027871683&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85027871683&partnerID=8YFLogxK
U2 - 10.1137/1.9781611974973.90
DO - 10.1137/1.9781611974973.90
M3 - Conference contribution
AN - SCOPUS:85027871683
T3 - Proceedings of the 17th SIAM International Conference on Data Mining, SDM 2017
SP - 804
EP - 812
BT - Proceedings of the 17th SIAM International Conference on Data Mining, SDM 2017
A2 - Chawla, Nitesh
A2 - Wang, Wei
PB - Society for Industrial and Applied Mathematics Publications
T2 - 17th SIAM International Conference on Data Mining, SDM 2017
Y2 - 27 April 2017 through 29 April 2017
ER -