The popularity of these visualization grammars is evident. As open-source packages, ggplot2 (R) has around 1.5 million down-Visualization grammars, often based on the Grammar of Graphics, are popular choices for specifying expressive visualizations and loads from CRAN per month 1 and Vega-Lite (JSON specifcation) supporting visualization systems. However, there are still open has 2 million CDN hits per month 2 . Users of visualization grammars are well beyond the visualization research community -journalquestions about grammar design and evaluation not well-answered in visualization research. In this SIG, we propose to discuss what ists use D3 3 and ggplot2 [5] in their reporting, and authors of ggplot2 books have background in felds like statistics [19] and makes a grammar "good" and explore evaluation methodologies sociology [4]. best suited for visualization grammars. Increasingly, visualization grammars have become building blocks for other formalisms and systems. To support data explo-CCS CONCEPTS ration and question answering in visual analysis, Voyager 2, a • Human-centered computing → Visualization design and mixed-initiative system, is powered through CompassQL, "a generevaluation methods; Visualization theory, concepts and alization of the Vega-Lite grammar" [14, 22]. To depict probability paradigms; Visualization application domains. distributions, A Probabilistic Grammar of Graphics makes probability expressions such as P(A|B) frst-class citizens on top of the KEYWORDS original GoG [13]. For high-performance visual analytics, P6 lever-Grammar of Graphics ages a declarative grammar to integrate interactive visualizations
Tukey emphasized decades ago that taking exploratory findings as confirmatory is “destructively foolish”. We reframe recent conversations about the reliability of results from exploratory visual analytics—such as the multiple comparisons problem—in terms of Gelman and Loken’s garden of forking paths to lay out a design space for addressing the forking paths problem in visual analytics. This design space encompasses existing approaches to address the forking paths problem (multiple comparison correction) as well as solutions that have not been applied to exploratory visual analytics (regularization). We also discuss how perceptual bias correction techniques may be used to correct biases induced in analysts’ understanding of their data due to the forking paths problem, and outline how this problem can be cast as a threat to validity within Munzner’s Nested Model of visualization design. Finally, we suggest paper review guidelines to encourage reviewers to consider the forking paths problem when evaluating future designs of visual analytics tools.
Visualizations depicting probabilities and uncertainty are used everywhere from medical risk communication to machine learning, yet these probabilistic visualizations are difficult to specify, prone to error, and their designs are cumbersome to explore. We propose a Probabilistic Grammar of Graphics (PGoG), an extension to Wilkinson's original framework. Inspired by the success of probabilistic programming languages, PGoG makes probability expressions, such as P(A|B), a firstclass citizen in the language. PGoG abstractions also reflect the distinction between probability and frequency framing, a concept from the uncertainty communication literature. It is expressive, encompassing product plots, density plots, icon arrays, and dotplots, among other visualizations. Its coherent syntax ensures correctness (that the proportions of visual elements and their spatial placement reflect the underlying probability distribution) and reduces edit distance between probabilistic visualization specifications, potentially supporting more design exploration. We provide a proof-of-concept implementation of PGoG in R.
Transparent research practices analytic methods, and data to be thoroughly evaluated and potentially reproduced. The HCI community has recognized research transparency as one quality aspect of paper submission and review since CHI 2021. This course addresses HCI researchers and students who are already knowledgeable about experiment research design and statistical analysis. Building upon this knowledge, we will present current best practices and tools for increasing research transparency. We will cover relevant concepts and skills in Open Science, frequentist statistics, and Bayesian statistics, and uncertainty visualization. In addition to lectures, there will be hands-on exercises: The course participants will assess transparency practices in excerpts of quantitative reports, interactively explore implications of analytical choices using RStudio Cloud, and discuss their fndings in small groups. In the fnal session, each participant will choose a case study based on their interest and assess its research transparency together with their classmates and instructors.enable the research design, materials,
CCS CONCEPTS• Human-centered computing → HCI design and evaluation methods; Visualization techniques; Visualization design and evaluation methods.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.