A comparative study of coherence, mutual information and cross-intensity models.

Ting Wang, Mark Bebbington, & David S. Harte

Published 2010, SCEC Contribution #6151

Coherence is a measure of the time invariant linear dependence of two processes at certain frequencies, and provides a measure of the degree
of linear predictability of one process from another process. The coherence is inadequate as a measure of general association for it may be identically 0 when two series are in fact related. However, such behavior does not occur for the coefficient of mutual information, which is a measure of the amount of information that one random variable contains about another random variable. The Lin-Lin model, which describes the influence of an input on a point process
output, can identify linear causal relationships between one sequence of events and another. This paper presents a comparative study of the three approaches using a case study of the relationship between roundwater level data from
Tangshan Well and global earthquakes with minimum magnitude 5.8.

Citation
Wang, T., Bebbington, M., & Harte, D. S. (2010). A comparative study of coherence, mutual information and cross-intensity models.. International Journal of Information and Systems Sciences, 6(1), 49-60. http://www.math.ualberta.ca/ijiss/SS-Volume-6-2010/No-1-10/SS-10-01-04.pdf