ABSTRACT
In 1975, John W. Tukey defined statistical data depth as a function that determines the centrality of an arbitrary point with respect to a data cloud or to a probability measure. During the last decades, this seminal idea of data depth evolved into a powerful tool proving to be useful in various fields of science. Recently, extending the notion of data depth to the functional setting attracted a lot of attention among theoretical and applied statisticians. We go further and suggest a notion of data depth suitable for data represented as curves, or trajectories, which is independent of the parameterization. We show that our curve depth satisfies theoretical requirements of general depth functions that are meaningful for trajectories. We apply our methodology to diffusion tensor brain images and also to pattern recognition of handwritten digits and letters. Supplementary materials for this article are available online.
Acknowledgments
The authors would like to express their deepest appreciation to the associate editor who provided a very valuable and extensive critique with many suggestions on an earlier version of this work. The authors are grateful to Wei Wen for providing the OATS dataset and to Zhaohua Ding and Sebastian Kurtek for providing the DT-MRI brain fibers dataset used in Section 6.2. We would like to thank Gery Geenens, Karl Mosler, and Lionel Truquet for fruitful discussions about theoretical aspects. This article includes results produced on the computational cluster Katana at UNSW Sydney.