New tools for analyzing time series relationships and trends

Geophysical studies are plagued by short and noisy time series. These time series are typically nonstationary contain various long‐period quasi‐periodic components, and have rather low signal‐to‐noise ratios and/or poor spatial sampling. Classic examples of these time series are tide gauge records, which are influenced by ocean and atmospheric circulation patterns, twentieth‐century warming, and other long‐term variability. Remarkable progress recently has been made in the statistical analysis of time series. Ghil et al . 2002 presented a general review of several advanced statistical methods with a solid theoretical foundation. This present article highlights several new approaches that are easy to use and that may be of general interest.