Contemporary computers bring us very large datasets, datasets which can be too large for those same computers to analyse properly. One approach is to aggregate these data (by some suitably scientific criteria) to provide more manageably-sized datasets. These aggregated data will perforce be symbolic data consisting of lists, intervals, histograms, etc. Now an observation is a p-dimensional hypercube or Cartesian product of p distributions in R<sup>p</sup>, instead of the p-dimensional point in in R<sup>p</sup> of classical data. Other data can be naturally symbolic. We give a brief overview of interval-valued data and show briefly that it is important to use symbolic analysis methodology since, e.g., analyses based on classical surrogates ignore some of the information in the dataset.
Billard, L. (2008). Some analyses of interval data. In Proceedings of the International Conference on Information Technology Interfaces, ITI (pp. 3–11). https://doi.org/10.1109/ITI.2008.4588377