Data Visualization

Visualization is a potent way to tell a story with your data.

W.E.B. Du Bois’ data portraits included in the the Exhibit of American Negroes at the Paris Exhibition of 1900 illustrate the power of effective visualization. With compelling hand-drawn graphics, Du Bois tells the story of what it means to be Black in post-Emancipation America as he translates sociological research and census data to reach beyond the academy. On the arts website Hyperallergic, Jasmine Weber has described “How W.E.B. Du Bois Meticulously Visualized 20th-Century Black America.”

Different types of visualization work best for different types of analysis. The table below, reproduced with minor modifications from the CUNY DHRI-Curriculum GitHub repository “Data Literacies,” (licensed CC-BY-SA), offers some examples.

Type of Analysis Type of Visualization When to Use Example of Visualization
Comparison Bar chart Comparison across distinct categories Bar Chart
Source: Data for Public Good at the CUNYGraduate Center
Histogram Comparison across continuous variable Histogram
Source: Policy Viz
Scatter plot Useful to check for correlation (not causation!) Scatter plot
Source: FiveThirtyEight
Time Stacked area chart Evolution of value across different groups Stacked area chart
Source: From Data to Viz
Sankey Diagram Displaying flows of changes Sankey
Source: From Data to Viz
Line graph Tracking changes over time Line Graph
Source: Data for Public Good at the CUNY Graduate Center
Small numbers/percentages Pie chart Demonstrate proportions between categories Pie chart
Source: Library of Congress
Tree map Demonstrate hierarchy and proportion Tree map
Source: The Data Visualization Catalogue
Survey responses Stacked bar chart Compares total amount across each group (e.g. plotting Likert scale) Stacked bar chart
Source: Library of Congress
Nested area graph Visualize branching/nested questions Nested area graph
Source: Evergreen Data
Place Choropleth map Visualize values over a geographic area to demonstrate pattern Choropleth map
Source: Library of Congress
Hex(bin) or Tile map Similar to Choropleth with the hexbin/tile representing regions equally rather than by geographic size Hexbin graph
Source: R Graph Gallery
Adapted from Stephanie D. Evergreen (2019) Effective data visualization: The right chart for the right data, The Data Visualization Catalogue, and From Data to Viz.