Comparing the Efficacy of Static and Dynamic Graph Types in Communicating Complex Statistical Relationships.

Area of Science:

• Data Visualization
• Human-Computer Interaction
• Cognitive Psychology

Background:

• Graphs effectively communicate data patterns, but efficacy depends on format and medium.
• Digital graphs offer dynamic manipulation, yet their effectiveness is understudied.
• Understanding variable interactions is crucial for data interpretation.

Purpose of the Study:

• To compare the effectiveness of static versus dynamic graphical formats in conveying relationship information, particularly variable interactions.
• To investigate how different graph types and relationship complexities affect data interpretation accuracy.

Main Methods:

• 128 undergraduates received a tutorial on data relationships (main effects, interactions).
• Participants answered 48 multiple-choice questions on graphs across four figure types and four relationship types.
• Multilevel logistic regression analyzed performance differences.

Main Results:

• Participants accurately detected main effects and null relationships but struggled with interaction effects.
• Static 3D graphs reduced performance for main effects, an effect mitigated by interactive rotation.
• No graph type fully resolved difficulties with complex relationships like interactions.

Conclusions:

• Dynamic figures in digital formats show potential for enhancing data communication.
• Interactive elements, like rotating 3D graphs, can improve comprehension of certain data aspects.
• Further research is needed on advanced dynamic formats and experienced populations for complex data visualization.