A Geometric Statistic for Quantifying Correlation Between Tree-Shaped Datasets

Abstract

The magnitude of Pearson correlation between two scalar random variables can be visually judged from the two-dimensional scatter plot of an independent and identically distributed sample drawn from the joint distribution of the two variables: the closer the points lie to a straight slanting line, the greater the correlation. To the best of our knowledge, similar graphical representation or geometric quantification of tree correlation does not exist in the literature although tree-shaped datasets are frequently encountered in various fields, such as academic genealogy tree and embryonic development tree. In this paper, we introduce a geometric statistic to both represent tree correlation intuitively and quantify its magnitude precisely. The theoretical properties of the geometric statistic are provided. Large-scale simulations based on various data distributions demonstrate that the geometric statistic is precise in measuring the tree correlation. Its real application on mathematical genealogy trees also demonstrated its usefulness.