Online Program

Saturday, October 22
Knowledge
Community
Influence
Sat, Oct 22, 5:20 PM - 6:20 PM
Salon 2
Speed Session 6

Visual Inference for Networks (303256)

Heike Hofmann, Iowa State University 
*Samantha Tyner, Iowa State University 

Keywords: statistical graphics, visual inference, human subject testing, SIENA models, network model diagnostics

The lineup protocol (Buja et al, 2009) has been shown to be an effective tool for quantifying the significance of graphical findings, in particular for linear models (Majumder et al, 2013). In this paper, we are applying the theory and methods of visual inference for network visualizations. Due to the high cognitive load involved in an exploration of graphs, we investigate the use of various lineup sizes. This allows us to assess the power of visually distinguishing between networks from different models.