Users often have access to multiple forecasts regarding an event.Different forecasts incorporate different assumptions and epistemic information.A growing body of work argues against decisionmaking solely based on expected utility maximisation strategies in multiple forecasts scenarios, in favour of other strategies such as the maximin expected utility.In this work, we compare two different approaches for depicting epistemic uncertainty-ensembles (a direct representation of multiple forecasts) and p-boxes (a representation which only communicates the bounds of epistemic uncertainty)-in plots where individual distributions are represented as cumulative distribution plots (CDFs).We conduct three experiments to investigate the impact of the visual representation on the decision-making strategies that people adopt.Our results suggest that participants adopt conservative decision-making strategies (i.e.place greater weight on the worst-case forecast than the best-case forecast) for both p-boxes and ensembles if the set of forecasts are uniformly distributed.However, if a majority of the forecasts are clustered near one of the bounds, participants may discount the forecast which appears as a visual outlier.

Given the scale at which online harassment occurs, researchers and practitioners alike have turned to computationally driven approaches to address it. However, because harassment is highly contextual and personal, designing effective solutions to this problem can be extremely challenging. This paper examines how harassment-mitigation systems studied in human-computer interaction (HCI) consider victim-centered principles in their design. Through a scoping literature review and close reading of 17 papers, we contribute—(1) a characterization of how novel and existing systems consider victims’ identity characteristics, definitions of harassment, and preferred strategies for dealing with harassment; (2) challenges faced by the systems along these dimensions to surface limitations, gaps, and tensions; (3) practical recommendations for researchers, designers, and practitioners to overcome these challenges. In doing so, we offer potential new directions to positively design computational approaches to addressing online harassment with victim-centered principles in mind.

Multiverse analyses involve conducting all combinations of reasonable choices in a data analysis process. A reader of a study containing a multiverse analysis might question—are all the choices included in the multiverse reasonable and equally justifiable? How much do results vary if we make different choices in the analysis process? In this work, we identify principles for validating the composition of, and interpreting the uncertainty in, the results of a multiverse analysis. We present Milliways, a novel interactive visualisation system to support principled evaluation of multiverse analyses. Milliways provides interlinked panels presenting result distributions, individual analysis composition, multiverse code specification, and data summaries. Milliways supports interactions to sort, filter and aggregate results based on the analysis specification to identify decisions in the analysis process to which the results are sensitive. To represent the two qualitatively different types of uncertainty that arise in multiverse analyses—probabilistic uncertainty from estimating unknown quantities of interest such as regression coefficients, and possibilistic uncertainty from choices in the data analysis—Milliways uses consonance curves and probability boxes. Through an evaluative study with five users familiar with multiverse analysis, we demonstrate how Milliways can support multiverse analysis tasks, including a principled assessment of the results of a multiverse analysis.

Recent studies have shown that users of visual analytics tools can have difficulty distinguishing robust findings in the data from statistical noise, but the true extent of this problem is likely dependent on both the incentive structure motivating their decisions, and the ways that uncertainty and variability are (or are not) represented in visualisations. In this work, we perform a crowd-sourced study measuring decision-making quality in visual analytics, testing both an explicit structure of incentives designed to reward cautious decision-making as well as a variety of designs for communicating uncertainty. We find that, while participants are unable to perfectly control for false discoveries as well as idealised statistical models such as the Benjamini-Hochberg, certain forms of uncertainty visualisations can improve the quality of participants’ decisions and lead to fewer false discoveries than not correcting for multiple comparisons. We conclude with a call for researchers to further explore visual analytics decision quality under different decision-making contexts, and for designers to directly present uncertainty and reliability information to users of visual analytics tools. The supplementary materials are available at: https://osf.io/xtsfz/.

There are myriad ways to analyse a dataset. But which one to trust? In the face of such uncertainty, analysts may adopt multiverse analysis: running all reasonable analyses on the dataset. Yet this is cognitively and technically difficult with existing tools—how does one specify and execute all combinations of reasonable analyses of a dataset?—and often requires discarding existing workflows. We present multiverse, a tool for implementing multiverse analyses in R with expressive syntax supporting existing computational notebook workflows. multiverse supports building up a multiverse through local changes to a single analysis and optimises execution by pruning redundant computations. We evaluate how multiverse supports programming multiverse analyses using (a) principles of cognitive ergonomics to compare with two existing multiverse tools; and (b) case studies based on semi-structured interviews with researchers who have successfully implemented an end-to-end analysis using multiverse. We identify design tradeoffs (e.g. increased flexibility versus learnability), and suggest future directions for multiverse tool design.

Most real-world datasets contain missing values yet most exploratory data analysis (EDA) systems only support visualising data points with complete cases. This omission may potentially lead the user to biased analyses and insights. Imputation techniques can help estimate the value of a missing data point, but introduces additional uncertainty. In this work, we investigate the effects of visualising imputed values in charts using different ways of representing data imputations and imputation uncertainty-no imputation, mean, 95% confidence intervals, probability density plots, gradient intervals, and hypothetical outcome plots. We focus on scatterplots, which is a commonly used chart type, and conduct a crowdsourced study with 202 participants. We measure users' bias and precision in performing two tasks-estimating average and detecting trend-and their self-reported confidence in performing these tasks. Our results suggest that, when estimating averages, uncertainty representations may reduce bias but at the cost of decreasing precision. When estimating trend, only hypothetical outcome plots may lead to a small probability of reducing bias while increasing precision. Participants in every uncertainty representation were less certain about their response when compared to the baseline. The findings point towards potential trade-offs in using uncertainty encodings for datasets with a large number of missing values. This paper and the associated analysis materials are available at: https://osf.io/q4y5r/.

Authors often transform a large screen visualization for smaller displays through rescaling, aggregation and other techniques when creating visualizations for both desktop and mobile devices (i.e., responsive visualization). However, transformations can alter relationships or patterns implied by the large screen view, requiring authors to reason carefully about what information to preserve while adjusting their design for the smaller display. We propose an automated approach to approximating the loss of support for task-oriented visualization insights (identification, comparison, and trend) in responsive transformation of a source visualization. We operationalize identification, comparison, and trend loss as objective functions calculated by comparing properties of the rendered source visualization to each realized target (small screen) visualization. To evaluate the utility of our approach, we train machine learning models on human ranked small screen alternative visualizations across a set of source visualizations. We find that our approach achieves an accuracy of 84% (random forest model) in ranking visualizations. We demonstrate this approach in a prototype responsive visualization recommender that enumerates responsive transformations using Answer Set Programming and evaluates the preservation of task-oriented insights using our loss measures. We discuss implications of our approach for the development of automated and semi-automated responsive visualization recommendation.

Bayesian statistical analysis is steadily growing in popularity and use. Choosing priors is an integral part of Bayesian inference. While there exist extensive normative recommendations for prior setting, little is known about how priors are chosen in practice. We conducted a survey (N = 50) and interviews (N = 9) where we used interactive visualizations to elicit prior distributions from researchers experienced withBayesian statistics and asked them for rationales for those priors. We found that participants' experience and philosophy influence how much and what information they are willing to incorporate into their priors, manifesting as different levels of informativeness and skepticism. We also identified three broad strategies participants use to set their priors: centrality matching, interval matching, and visual mass allocation. We discovered that participants' understanding of the notion of 'weakly informative priors"-a commonly-recommended normative approach to prior setting-manifests very differently across participants. Our results have implications both for how to develop prior setting recommendations and how to design tools to elicit priors in Bayesian analysis.

We present explorable multiverse analysis reports, a new approach to statistical reporting where readers of research papers can explore alternative analysis options by interacting with the paper itself. This approach draws from two recent ideas: i) multiverse analysis, a philosophy of statistical reporting where paper authors report the outcomes of many different statistical analyses in order to show how fragile or robust their findings are; and ii) explorable explanations, narratives that can be read as normal explanations but where the reader can also become active by dynamically changing some elements of the explanation. Based on five examples and a design space analysis, we show how combining those two ideas can complement existing reporting approaches and constitute a step towards more transparent research papers.

We present the design and preliminary evaluation of a mobile text-based system and that provides homeless people in the United States with information about the availability of free meals. The system, piloted in Ann Arbor, Michigan, provides information about when and where free meals are offered based on zipcode as entered by users. It has features to address issues around information access, incompleteness, and irrelevance. We found that SMS text messages are preferred by our homeless users even when they are non-literate and own smartphones, and that formal systems are useful even in contexts where word-of-mouth predominates.