Statdepth: a package for analysis of functional and pointcloud data using statistical depth

Abstract

Laboratory scientists are well equipped with statistical tools for univariate data, yet many phenomena of scientific interest are time-variant or otherwise multidimensional. Functional data analysis is one way of approaching such data: by representing these more complex data as single data points in a mathematical space of functions. The mathematical concept of functional depth provides a notion of centrality which allows for descriptive statistics and some comparative statistics on these data. Here, we present statdepth, a Python package for functional depth-based analyses which naturally extends familiar single-data-point L-statistics and related methods to time-variant data trajectories or multidimensional data.