A Systematic Review of Experimental Studies on Data Glyphs

High-throughput experiments, such as gene expression microarrays in the life sciences, result in very large data sets. In response, a wide variety of visualization tools have been created to facilitate data analysis. A primary purpose of these tools is to provide biologically relevant insight into the data. Typically, visualizations are evaluated in controlled studies that measure user performance on predetermined tasks or using heuristics and expert reviews. To evaluate and rank bioinformatics visualizations based on real-world data analysis scenarios, we developed a more relevant evaluation method that focuses on data insight. This paper presents several characteristics of insight that enabled us to recognize and quantify it in open-ended user tests. Using these characteristics, we evaluated five microarray visualization tools on the amount and types of insight they provide and the time it takes to acquire it. The results of the study guide biologists in selecting a visualization tool based on the type of their microarray data, visualization designers on the key role of user interaction techniques, and evaluators on a new approach for evaluating the effectiveness of visualizations for providing insight. Though we used the method to analyze bioinformatics visualizations, it can be applied to other domains.

People have difficulty understanding statistical information and are unaware of their wrong judgments, particularly in Bayesian reasoning. Psychology studies suggest that the way Bayesian problems are represented can impact comprehension, but few visual designs have been evaluated and only populations with a specific background have been involved. In this study, a textual and six visual representations for three classic problems were compared using a diverse subject pool through crowdsourcing. Visualizations included area-proportional Euler diagrams, glyph representations, and hybrid diagrams combining both. Our study failed to replicate previous findings in that subjects' accuracy was remarkably lower and visualizations exhibited no measurable benefit. A second experiment confirmed that simply adding a visualization to a textual Bayesian problem is of little help, even when the text refers to the visualization, but suggests that visualizations are more effective when the text is given without numerical values. We discuss our findings and the need for more such experiments to be carried out on heterogeneous populations of non-experts.