CDS 6324 - Data Visualization

Lecture 2: Data & Image Models

1. Data Models vs Conceptual Models

Data models are formal descriptions of data. Conceptual models are the meanings humans attach to data.
Data Model Conceptual Model
1D Float Temperature
3D Vector Spatial Location
🧠 Remember:

Data Model = Structure
Conceptual Model = Meaning

2. Taxonomy of Data Types

🧠 Memory Trick:

Sequence → Time → Map → Shape → Table → Tree → Graph

3. Qualitative vs Quantitative Data

Qualitative Quantitative
Observed Measured
Gender Age
Country Height
Hair Color Weight
🧠 Shortcut:

Qualitative = WHAT
Quantitative = HOW MUCH

4. Nominal (N)

Categories without order or ranking.
Examples:
  • Gender
  • Country
  • Hair Color
Operations: Frequency Count, Percentage, Mode
Common Charts: Bar Chart, Pie Chart, Treemap

5. Ordinal (O)

Categories with meaningful order.
Examples:
  • Gold Medal
  • Silver Medal
  • Bronze Medal
Operations: Rank, Median, Frequency Count
Common Charts: Ordered Bar Charts, Dot Plots

6. Quantitative Data (Q)

Type Description
Interval No true zero point
Ratio Has a true zero point
Interval Example: Temperature (°C)
Ratio Example: Population Count

7. Dimensions vs Measures

Dimensions Measures
Categories Numbers
Year Sales
Gender Revenue
🧠 Easy Rule:

Dimensions describe.
Measures calculate.

8. Census Data Example

Variable Type
People Count Q-Ratio
Year Q-Interval
Age Q-Ratio
Sex Nominal
Marital Status Nominal

9. Relational Data Model

Data is organized into tables (relations).
Term Meaning
Row Record
Column Attribute
Table Relation

10. SQL Operations

Operation Purpose
SELECT Choose columns
WHERE Filter rows
ORDER BY Sort rows
GROUP BY Aggregate data
JOIN Combine tables

11. Roll-Up and Drill-Down

Roll-Up = Summarize data
Drill-Down = Show more detail
🧠 Roll-Up = Zoom Out
🧠 Drill-Down = Zoom In

12. Tidy Data

Data organization standard proposed by Wickham.
Frequently tested concept in data visualization.

13. Bertin's Visual Variables

Visual Variable Best For
PositionQuantitative
SizeQuantitative
Color HueNominal
ValueOrdinal
ShapeNominal
🧠 Position is the strongest visual encoding.

14. Expressiveness & Effectiveness

Expressiveness: A visualization should show all facts and only the facts.
Effectiveness: Information should be easy for humans to perceive.
🧠 Expressive = Correct
🧠 Effective = Easy to Read

15. Final Exam Summary

Most Important Points

  • N: Nominal = Categories
  • O: Ordinal = Ordered Categories
  • Q: Quantitative = Numeric Values
  • Dimensions: Describe data
  • Measures: Analyze data
  • Tidy Data: Variable = Column, Observation = Row
  • Bertin: Position is the strongest visual channel.
  • Expressiveness: Show correct facts.
  • Effectiveness: Easy to perceive.