Online Program Home
  My Program

Abstract Details

Activity Number: 344 - Technology in the Classroom
Type: Contributed
Date/Time: Tuesday, August 1, 2017 : 10:30 AM to 12:20 PM
Sponsor: Section on Statistical Education
Abstract #324732 View Presentation
Title: Evaluating Change in Learning from Different Forms of Interactive Visualizations with a Large Case Study.
Author(s): Lata Kodali* and Peter Hauck and Michelle Dowling and Leanna House and Scotland Leman and Chris North
Companies: and Virginia Tech, Discovery Analytics Center and Virginia Tech, Department of Computer Science and Virginia Tech, Department of Statistics and Virginia Tech and Virginia Tech, Department of Computer Science
Keywords: Bayesian ; Education ; Multidimensional Scaling ; Visual Analytics

In previous work, we developed cutting edge software that allows novice analysts to explore high-dimensional data interactively called Andromeda (House et al. 2010; Endert et al. 2011; Self et al. 2016). It enables users to explore high-dimensional data using multiple linear projections based on Weighted Multidimensional Scaling (WMDS) (Kruskal 1964). The direction for which data are projected in WMDS is determined by weights assigned to each variable. In Andromeda, the WMDS weights are set in response to users interactions with the data. Interactions include surface level, parametric, object level, and/or any combination of these (Leman et al. 2013). In this paper, we evaluate the impact of student learning on each interaction via a large scale user study. This study includes approximately 200 students grouped by four different recitation periods with each randomly assigned one of four versions of Andromeda. All versions have surface level interactions capabilities, and only three of them have additional interaction features. Using a Bayesian approach, we share our findings from this user study including significant differences in mastery of WMDS and complexity of insights.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2017 program

Copyright © American Statistical Association