Title: HistDAWass package: An R tool for forecasting histogram-valued data
Authors: Javier Arroyo - Universidad Complutense de Madrid (Spain) [presenting]
Antonio Irpino - Second University of Naples (Italy)
Abstract: In the framework of Symbolic Data Analysis, a relatively new approach to the statistical analysis of multi-valued data, we consider histogram-valued data, i.e. where each statistical unit is described by several univariate histograms. This approach is appropriate to analyze statistical units that aggregate a set of values. We present the HistDAWass package for R, which includes statistical methods to analyze this kind of data. The methods and the basic statistics for histogram-valued data are mainly based on the $L_2$ Wasserstein metric between distributions, i.e. a Euclidean metric between quantile functions. The package contains unsupervised classification techniques, least squared regression and tools for histogram-valued data and for histogram time series. We will show the main features of the package and applications to histogram-valued datasets extracted from different real-life contexts.