Volume 36 - Article 21 | Pages 627–658 Author has provided data and code for replicating results

Visualizing compositional data on the Lexis surface

By Jonas Schöley, Frans Willekens

Print this page  Facebook  Twitter


Date received:21 Aug 2015
Date published:17 Feb 2017
Word count:6000
Keywords:cause of death, color scale, compositional data, data visualization, France, Lexis surface, mortality
Additional files:readme.36-21 (text file, 807 Byte)
 demographic-research.36-21 (zip file, 765 kB)


Background: The Lexis surface plot is an established visualization tool in demography. Its present utility, however, is limited to the domain of one-dimensional magnitudes such as rates and counts. Visualizing proportions among three or more groups on a period-age grid is an unsolved problem.

Objective: We seek to extend the Lexis surface plot to the domain of compositional data.

Methods: We propose four techniques for visualizing group compositions on a period-age grid. To demonstrate the techniques we use data on age-specific cause-of-death compositions in France from 1925 to 1999. We compare the visualizations for compliance with multiple desired criteria.

Results: Compositional data can effectively be visualized on the Lexis surface. A key feature of the classical Lexis surface plot – to show age, period, and cohort patterns – is retained in the domain of compositions. The optimal choice among the four proposed techniques depends primarily on the number of groups making up the composition and whether or not the plot should be readable by people with impaired colour vision.

Contribution: We introduce techniques for visualizing compositional data on a period-age grid to the field of demography and demonstrate the usefulness of the techniques by performing an exploratory analysis of age-specific French cause-of-death patterns across the 20th century. We identify strengths and weaknesses of the four proposed techniques. We contribute a technique to construct the ternary-balance colour scheme from within a per- ceptually uniform colour space.

Comments: A full-colour representation is key to understanding the paper. Therefore, we recommend that you read it on screen or print a colour version.

Author's Affiliation

Jonas Schöley - Syddansk Universitet, Denmark [Email]
Frans Willekens - Nederlands Interdisciplinair Demografisch Instituut (NIDI), the Netherlands [Email]

Other articles by the same author/authors in Demographic Research

» The centered ternary balance scheme: A technique to visualize surfaces of unbalanced three-part compositions
Volume 44 - Article 19

» Interdisciplinary Research on Healthy Aging: Introduction
Volume 38 - Article 10

» Software for multistate analysis
Volume 31 - Article 14

» Chronological objects in demographic research
Volume 28 - Article 23

Most recent similar articles in Demographic Research

» Exploring the demographic history of populations with enhanced Lexis surfaces
Volume 42 - Article 6    | Keywords: data visualization, Lexis surface, mortality

» Revisiting the mortality of France and Italy with the multiple-cause-of-death approach
Volume 23 - Article 28    | Keywords: cause of death, France, mortality

» Using multiple cause of death information to eliminate garbage codes
Volume 45 - Article 11    | Keywords: cause of death, mortality

» The centered ternary balance scheme: A technique to visualize surfaces of unbalanced three-part compositions
Volume 44 - Article 19    | Keywords: compositional data, data visualization

» A visual tool to explore the composition of international migration flows in the EU countries, 1998–2015
Volume 42 - Article 27    | Keywords: compositional data, data visualization