Visualization of Uncertainty without a Mean

IEEE Transactions on Visualization and Computer Graphics, 2000

AbstractMany techniques have been proposed to show uncertainty in data visualizations. However, very little is known about their effectiveness in conveying meaningful information. In this paper, we present a user study that evaluates the perception of uncertainty amongst four of the most commonly used techniques for visualizing uncertainty in one-dimensional and twodimensional data. The techniques evaluated are traditional errorbars, scaled size of glyphs, color-mapping on glyphs, and colormapping of uncertainty on the data surface. The study uses generated data that was designed to represent the systematic and random uncertainty components. Twenty-seven users performed two types of search tasks and two types of counting tasks on 1D and 2D datasets. The search tasks involved finding data points that were least or most uncertain. The counting tasks involved counting data features or uncertainty features. A 4 4 full-factorial ANOVA indicated a significant interaction between the techniques used and the type of tasks assigned for both datasets indicating that differences in performance between the four techniques depended on the type of task performed. Several one-way ANOVAs were computed to explore the simple main effects. Bonferronnis correction was used to control for the family-wise error rate for alpha-inflation. Although we did not find a consistent order among the four techniques for all the tasks, there are several findings from the study that we think are useful for uncertainty visualization design. We found a significant difference in user performance between searching for locations of high and searching for locations of low uncertainty. Errorbars consistently underperformed throughout the experiment. Scaling the size of glyphs and color-mapping of the surface performed reasonably well. The efficiency of most of these techniques were highly dependent on the tasks performed. We believe that these findings can be used in future uncertainty visualization design. In addition, the framework developed in this user study presents a structured approach to evaluate uncertainty visualization techniques, as well as provides a basis for future research in uncertainty visualization.

Innovative Approaches of Data Visualization and Visual Analytics (DVVA 2013), 2013

While uncertainty in scientific data attracts an increasing research interest in the visualization community, two critical issues remain insufficiently studied: (1) visualizing the impact of the uncertainty of a data set on its features and (2) interactively exploring 3D or large 2D data sets with uncertainties. In this chapter, a suite of feature-based techniques is developed to address these issues. First, an interactive visualization tool for exploring scalar data with data-level, contour-level, and topology-level uncertainties is developed. Second, a framework of visualizing feature-level uncertainty is proposed to study the uncertain feature deviations in both scalar and vector data sets. With quantified representation and interactive capability, the proposed feature-based visualizations provide new insights into the uncertainties of both data and their features which otherwise would remain unknown with the visualization of only data uncertainties.

Expanding the Frontiers of Visual Analytics and Visualization, 2012

Universities of Leeds, Sheffield and York http://eprints.whiterose.ac.uk/ This is an author produced version of a book chapter published in Expanding the Frontiers of Visual Analytics and Visualization.

Computer Graphics Forum, 2010

The graphical depiction of uncertainty information is emerging as a problem of great importance. Scientific data sets are not considered complete without indications of error, accuracy, or levels of confidence. The visual portrayal of this information is a challenging task. This work takes inspiration from graphical data analysis to create visual representations that show not only the data value, but also important characteristics of the data including uncertainty. The canonical box plot is reexamined and a new hybrid summary plot is presented that incorporates a collection of descriptive statistics to highlight salient features of the data. Additionally, we present an extension of the summary plot to two dimensional distributions. Finally, a use-case of these new plots is presented, demonstrating their ability to present high-level overviews as well as detailed insight into the salient features of the underlying data distribution.

2017

Geospatial information has become more accessible since the early 2000s. Uncertainty has remained a constant in data, due to various factors, including scale and real world conceptualization. Geospatial products are frequently used to inform decision makers on key decisions, with little understanding of the quality of the data. However, accuracy assessments have improved significantly since the visual screening that was used in the 1950s, now providing statistics such as the Kappa coefficient, root mean square error (RMSE) and the confusion matrix. Two questions thus arise: 1) do those using the data inform themselves about the quality of data; and 2) can visualization of the uncertainty in spatial data aid in the communication of the data quality? This research was achieved in three tasks: 1) evaluate the South African perception on data quality; 2) develop an uncertainty visualization tool; 3) evaluate the uncertainty visualization tool. The first task was achieved through a quant...

Computer Graphics Forum, 2013

An uncertain (scalar, vector, tensor) field is usually perceived as a discrete random field with a priori unknown probability distributions. To compute derived probabilities, e.g. for the occurrence of certain features, an appropriate probabilistic model has to be selected. The majority of previous approaches in uncertainty visualization were restricted to Gaussian fields. In this paper we extend these approaches to nonparametric models, which are much more flexible, as they can represent various types of distributions, including multimodal and skewed ones. We present three examples of nonparametric representations: (a) empirical distributions, (b) histograms and (c) kernel density estimates (KDE). While the first is a direct representation of the ensemble data, the latter two use reconstructed probability density functions of continuous random variables. For KDE we propose an approach to compute valid consistent marginal distributions and to efficiently capture correlations using a...

We present a variant of the Taylor diagram, a type of 2D plot that succinctly shows the relationship between two or more random variables based on their variance and correlation. The Taylor diagram has been adopted by the climate and geophysics communities to produce insightful visualizations, e.g., for intercomparison studies. Our variant, which we call the Mutual Information Diagram, represents the relationship between random variables in terms of their entropy and mutual information, and naturally maps well-known statistical quantities to their information-theoretic counterparts. Our new diagram is able to describe non-linear relationships where linear correlation may fail; it allows for categorical and multi-variate data to be compared; and it incorporates the notion of uncertainty, key in the study of large ensembles of data.

In recent years, a number of algorithms have been developed which provide fast approximate computations on large datasets. There is considerable interest in exploiting these techniques to render interactive visualisations of large datasets. Such interactions require careful consideration of the uncertainty arising from the approximations that these algorithms employ. Characterising and comparing visualisations of uncertainty has been well studied; however, it is typically assumed that uncertainty is a fixed property of the data. In light of this new generation of approximate visualisations, we consider the case where uncertainty arises from algorithms whose parameters can be altered, and so can be manipulated just like any other aspect of the visualisation. We present a novel direct manipulation interface for uncertainty in visualisations and show through a user study that our interface enables people to successfully edit and comprehend uncertainty.

2005

Recent emerging aspects of clinical data analysis, especially of high dimensional data such as genomic studies of microarrays, have begun to exploit interactive visualisation tools for exploratory data mining. However, existing tools have not been designed to accommodate uncertainty in the data measurements, even when estimates are available. In this work we show how it is possible to incorporate knowledge of uncertainty in data measurements in influencing the data representation in two modern visualisation tools: NeuroScale and the Generative Topographic Mapping (GTM). The approaches are illustrated on selected synthetic data problems and a microarray dataset of importance to pharmacogenetics research.