IEEE VIS 2024 Content: Causal Priors and Their Influence on Judgements of Causality in Visualized Data

Causal Priors and Their Influence on Judgements of Causality in Visualized Data



Arran Zeyu Wang - University of North Carolina-Chapel Hill, Chapel Hill, United States

 David Borland - UNC-Chapel Hill, Chapel Hill, United States

 Tabitha C. Peck - Davidson College, Davidson, United States

 Wenyuan Wang - University of North Carolina, Chapel Hill, United States

 David Gotz - University of North Carolina, Chapel Hill, United States

 Download Supplemental Material

 Room: Bayshore II

2024-10-16T14:51:00ZGMT-0600Change your timezone on the schedule page
2024-10-16T14:51:00Z

Exemplar figure, described by caption below — Results of participant-rated causal relationships for 56 concept pairs from open-source datasets. Participants rated the causal impact of X on Y for each pair on a scale of 1 to 5. The Y-axis in (a) shows these scores, ordered by mean causal relation on the X-axis with 95% confidence intervals. The light blue band represents the mean score +/- one standard deviation (SD). Vertical dashed lines indicate low (<mean-SD) and high (>mean+SD) causal priors. (b) presents heat maps for four example pairs, showing participant scores. The study highlights the variability in causal priors and their impact on visualization interpretation.

Fast forward

Keywords

Causal inference, Perception and cognition, Causal prior, Association, Causality, Visualization

Abstract

``Correlation does not imply causation'' is a famous mantra in statistical and visual analysis. However, consumers of visualizations often draw causal conclusions when only correlations between variables are shown. In this paper, we investigate factors that contribute to causal relationships users perceive in visualizations. We collected a corpus of concept pairs from variables in widely used datasets and created visualizations that depict varying correlative associations using three typical statistical chart types. We conducted two MTurk studies on (1) preconceived notions on causal relations without charts, and (2) perceived causal relations with charts, for each concept pair. Our results indicate that people make assumptions about causal relationships between pairs of concepts even without seeing any visualized data. Moreover, our results suggest that these assumptions constitute causal priors that, in combination with visualized association, impact how data visualizations are interpreted. The results also suggest that causal priors may lead to over- or under-estimation in perceived causal relations in different circumstances, and that those priors can also impact users' confidence in their causal assessments. In addition, our results align with prior work, indicating that chart type may also affect causal inference. Using data from the studies, we develop a model to capture the interaction between causal priors and visualized associations as they combine to impact a user's perceived causal relations. In addition to reporting the study results and analyses, we provide an open dataset of causal priors for 56 specific concept pairs that can serve as a potential benchmark for future studies. We also suggest remaining challenges and heuristic-based guidelines to help designers improve visualization design choices to better support visual causal inference.