• Home
• Fundamentals
  Introduction What is statistics Terms connected to data Measurement levels Significance SPSS basics
• One variable
  Introduction a binary variable a nominal variable an ordinal variable a scale variable
• Two variables - unpaired
  Introduction binary vs binary binary vs ordinal binary vs scale nominal vs nominal nominal vs ordinal nominal vs scale ordinal vs ordinal ordinal vs scale scale vs scale
• Two variables - paired
  Introduction two nominal two ordinal two scale
• 3+ variables - paired
  Introduction 3+ binary 3+ ordinal 3+ scale
• Distributions
  Introduction Binomial Bivariate Normal Chi-Square (Standard) Normal Student t Wilcoxon (Signed Rank)
• Search

Binary vs. Nominal

Visualisation

We can use any of the visualisations discussed in the Nominal vs. Nominal section. If you have a clear dependent and independent variable, then a so-called clustered bar-chart might be useful. However specifically if the independent variable is the binary one, a Pyramid(/Butterfly/Tornado/Divergent Bar) chart might be a good option. If you do not have a clear independent and dependent variable a spine plot could be a good choice.

Butterfly/Pyramid/Tornado/Funnel Chart

In the case of an independent binary variable, and dependent nominal a chart that is showing the bar-charts for each of the two categories, back to back is useful. The terminology for this kind of chart is very unclear. I use the following. Since a pyramid has a large base and a small top, I will consider in the case of a nominal variable the pyramid chart to be sorted like that, a tornado chart is then the opposite (large top, small base) and the same as a funnel chart. If there is no sorting a butterfly chart. The butterfly chart is then a special case of a divergent bar chart. A divergent bar chart could be for multiple bars that are each split in multiple parts, while the butterfly are multiple bars each split in only two.

The term 'back-to-back' is also sometimes added, since in theory you could make a Butterfly/Pyramid/Tornado/Funnel Chart with just one variable, and not split this between two categories. In practice though I hardly ever see this being done.

Figure 1 shows an example of the three diagrams (Butterfly, Pyramid and Tornado/Funnel)

Figure 1.
Butterfly, Pyramid, and Tornado Chart.

As can be seen from figure 1, the data is the same, just a different ordering. It seems that for both Male and Female the order of the categories is the same (most male were married, and most female as well, then never married, etc.). There don't seem to be any categories with large differences between male and female, but we can test if there still might be.

The other alternative charts mentioned were the clustered bar-chart and the spine plot. An example for each is shown below

Clustered (or Multiple) Bar Chart

See the visualisation section at Nominal vs. Nominal for more info on Clustered bar chart

Spine Plot

See the visualisation section at Nominal vs. Nominal for more info on Spine Plots

All of the charts don't seem to show any big differences between the male and females, but we can test if there still might be.

Binary vs. Binary

Introduction

Impression

Visualisation

Test

Effect Size

Reporting

Google adds