More Like this

1. Visual (dis)Confirmation: Validating Models and Hypotheses with Visualizations

   https://doi.org/10.1109/IV-2.2019.00032  

   Choi, In Kwon; Raveendranath, Nirmal Kumar; Westerfield, Jared; Reda, Khairi (July 2019, 23rd International Conference in Information Visualization – Part II)

   Data visualization provides a powerful way for analysts to explore and make data-driven discoveries. However, current visual analytic tools provide only limited support for hypothesis-driven inquiry, as their built-in interactions and workflows are primarily intended for exploratory analysis. Visualization tools notably lack capabilities that would allow users to visually and incrementally test the fit of their conceptual models and provisional hypotheses against the data. This imbalance could bias users to overly rely on exploratory analysis as the principal mode of inquiry, which can be detrimental to discovery. In this paper, we introduce Visual (dis) Confirmation, a tool for conducting confirmatory, hypothesis-driven analyses with visualizations. Users interact by framing hypotheses and data expectations in natural language. The system then selects conceptually relevant data features and automatically generates visualizations to validate the underlying expectations. Distinctively, the resulting visualizations also highlight places where one's mental model disagrees with the data, so as to stimulate reflection. The proposed tool represents a new class of interactive data systems capable of supporting confirmatory visual analysis, and responding more intelligently by spotlighting gaps between one's knowledge and the data. We describe the algorithmic techniques behind this workflow. We also demonstrate the utility of the tool through a case study. 

   more » « less
2. Visualization model validation via inline replication

   https://doi.org/10.1177/1473871618821747  

   Gotz, David; Wang, Wenyuan; Chen, Annie_T; Borland, David (January 2019, Information Visualization)

   Data visualizations typically show a representation of a data set with little to no focus on the repeatability or generalizability of the displayed trends and patterns. However, insights gleaned from these visualizations are often used as the basis for decisions about future events. Visualizations of retrospective data therefore often serve as “visual predictive models.” However, this visual predictive model approach can lead to invalid inferences. In this article, we describe an approach to visual model validation called Inline Replication. Inline Replication is closely related to the statistical techniques of bootstrap sampling and cross-validation and, like those methods, provides a non-parametric and broadly applicable technique for assessing the variance of findings from visualizations. This article describes the overall Inline Replication process and outlines how it can be integrated into both traditional and emerging “big data” visualization pipelines. It also provides examples of how Inline Replication can be integrated into common visualization techniques such as bar charts and linear regression lines. Results from an empirical evaluation of the technique and two prototype Inline Replication–based visual analysis systems are also described. The empirical evaluation demonstrates the impact of Inline Replication under different conditions, showing that both (1) the level of partitioning and (2) the approach to aggregation have a major influence over its behavior. The results highlight the trade-offs in choosing Inline Replication parameters but suggest that using [Formula: see text] partitions is a reasonable default. 

   more » « less
3. Assessing the fit of the multi-species network coalescent to multi-locus data

   https://doi.org/10.1093/bioinformatics/btaa863  

   Cai, Ruoyi; Ané, Cécile (December 2020, Bioinformatics)

   Russell, Schwartz (Ed.)

   Abstract Motivation With growing genome-wide molecular datasets from next-generation sequencing, phylogenetic networks can be estimated using a variety of approaches. These phylogenetic networks include events like hybridization, gene flow or horizontal gene transfer explicitly. However, the most accurate network inference methods are computationally heavy. Methods that scale to larger datasets do not calculate a full likelihood, such that traditional likelihood-based tools for model selection are not applicable to decide how many past hybridization events best fit the data. We propose here a goodness-of-fit test to quantify the fit between data observed from genome-wide multi-locus data, and patterns expected under the multi-species coalescent model on a candidate phylogenetic network. Results We identified weaknesses in the previously proposed TICR test, and proposed corrections. The performance of our new test was validated by simulations on real-world phylogenetic networks. Our test provides one of the first rigorous tools for model selection, to select the adequate network complexity for the data at hand. The test can also work for identifying poorly inferred areas on a network. Availability and implementation Software for the goodness-of-fit test is available as a Julia package at https://github.com/cecileane/QuartetNetworkGoodnessFit.jl. Supplementary information Supplementary data are available at Bioinformatics online. 

   more » « less
4. Co-Designing Data Labs at the Public Library: Data Literacy with, for, and by Teens

   Bowler, Leanne; Rosin, Mark; Lopatovska, I.; Vroom, L. (January 2022, iConference 2022)

   Presents research investigating youth data literacy at the public library. The Data Literacy with, for, and by Youth project is framed by principles of participatory design, and asks, how might an informal STEM learning environment such as the public library, support the development of the skills, knowledge, and dispositions that young people need for them to take charge of their data lives, from data creation to data use – to be, in short, data literate. The problem of how to approach something as complex as data literacy in the voluntary drop-in setting of informal, after-school sites of learning - the public library being one such place - guides this study. The aim of the project is to design, build, test, and evolve theory and practice around informal data literacy education alongside youth, with the goal of building a holistic, humanistic, and youth-oriented model of data literacy which incorporates social-awareness, critical approaches, and “goodness of fit” into STEM learning about data. 

   more » « less
5. Template-based piecewise affine regression

   https://doi.org/10.1017/cbp.2024.3  

   Berger, Guillaume O; Sankaranarayanan, Sriram (January 2024, Research Directions: Cyber-Physical Systems)

   Abstract We study the problem of fitting a piecewise affine (PWA) function to input–output data. Our algorithm divides the input domain into finitely many regions whose shapes are specified by a user-provided template and such that the input–output data in each region are fit by an affine function within a user-provided error tolerance. We first prove that this problem is NP-hard. Then, we present a top-down algorithmic approach for solving the problem. The algorithm considers subsets of the data points in a systematic manner, trying to fit an affine function for each subset using linear regression. If regression fails on a subset, the algorithm extracts a minimal set of points from the subset (an unsatisfiable core) that is responsible for the failure. The identified core is then used to split the current subset into smaller ones. By combining this top-down scheme with a set-covering algorithm, we derive an overall approach that provides optimal PWA models for a given error tolerance, where optimality refers to minimizing the number of pieces of the PWA model. We demonstrate our approach on three numerical examples that include PWA approximations of a widely used nonlinear insulin–glucose regulation model and a double inverted pendulum with soft contacts. 

   more » « less