Compare and rank
Glyph plot
Maps variables to features of repeated symbols to compare observation profiles.
- Plot
- Multivariate comparison
- Pattern recognition
What it answers
How do records differ across several encoded features?
- Shape
- Symbols with variable properties
- What it shows
- Profile patterns and outliers.
Example
The question
How do regions compare on several measures, placed by size and growth?
Regions as star glyphs placed by revenue and growth
Illustrative data. It belongs to no company.
When to use it
Use it when
Repeated multivariate summaries in a consistent layout.
Avoid it when
Too many encodings or unequal perceptual prominence.
How to read it
Read the glyph key before comparing size, orientation or shape features.
Note
Define each feature mapping and its scale.
The data you need
- Layout
- Wide observation table
- Fields
- ObservationID: text; V1...Vp: numeric columns
- One row is
- One observation with several measured numeric variables. What is the grain?
- Rules
- Align variables by observation. Decide scaling, missing-data handling and which columns are features.
- Optional
- Optional Group. PCA, clustering and correlations require calculations before rendering their derived results.
- Preparation
- Choose a consistent visual-feature mapping and scaling for every glyph before rendering.
- Units
- State the unit of every coordinate/variable. A unitless transformed or standardised scale must be identified; no common denominator is assumed.
Worked example
Map volume to area and direction to angle. Two records with equal volume have equal areas even if their angles differ.
| ID | V1 | V2 | V3 |
|---|---|---|---|
| A | 10 | 30 | 5 |
| B | 12 | 20 | 8 |
| C | 18 | 25 | 6 |