• Lloyd Allison


Multivariate data is where each datum d is a k-tuple of k > 1 components (fields), d = 〈d1, d2, …, d k 〉, and hence a data-set has more than one column. We have already encountered a special case of bivariate data where the relationship between an input datum (independent variable) and an output datum (dependent variable) is modelled by a function-model (Chap.  5). Note that a component need not be atomic (univariate), for example, field d2 could have sub-fields d2.1 and d2.2, say. Two components need not have the same type, for example, the data on a person in a certain data-set might consist of name (String), gender (Discrete, {m, f}), age (\( \mathbb {N}_{\ge 0} \)), height (\( \mathbb {R}_{\ge 0} \)), and weight (\( \mathbb {R}_{\ge 0} \)).


  1. 9.
    R. Bird, P. Wadler, Introduction to Functional Programming (Prentice Hall, Englewood, Cliffs, NJ, 1988). ISBN 978-0134841892Google Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  • Lloyd Allison
    • 1
  1. 1.Faculty of Information TechnologyMonash UniversityMelbourneAustralia

Personalised recommendations