Paul Murrell

Escaping RGBland: Selecting colors for statistical graphics

Statistical graphics are often augmented by the use of color coding information contained in some variable. When this involves the shading of areas (and not only points or lines)-e.g., as in bar plots, pie charts, mosaic displays or heatmaps-it is important that the colors are perceptually based and do not introduce optical illusions or systematic bias. Based on the perceptually-based Hue-Chroma-Luminance (HCL) color space suitable color palettes are derived for coding categorical data (qualitative palettes) and numerical variables (sequential and diverging palettes).

Data Science in Statistics Curricula: Preparing Students to “Think with Data”

A growing number of students are completing undergraduate degrees in statistics and entering the workforce as data analysts. In these positions, they are expected to understand how to use databases and other data warehouses, scrape data from Internet sources, program solutions to complex problems in multiple languages, and think algorithmically as well as statistically. These data science topics have not traditionally been a major component of undergraduate programs in statistics. Consequently, a curricular shift is needed to address additional learning outcomes. The goal of this article is to motivate the importance of data science proficiency and to provide examples and resources for instructors to implement data science in their own statistics curricula. We provide case studies from seven institutions. These varied approaches to teaching data science demonstrate curricular innovations to address new needs. Also included here are examples of assignments designed for courses that foster engagement of undergraduates with data and data science. [Received November 2014. Revised July 2015.]

An Approach to Providing Mathematical Annotation in Plots

Abstract A simple method for providing mathematical annotation of plots produced with the R environment is described. Although the implementation is specific to R, a similar method could be used in any environment which uses an expression-based command interface and provides a basic quoting mechanism.

Layouts: A Mechanism for Arranging Plots on a Page

Abstract An arbitrary arrangement of plots on a page can be achieved by specifying the location (left, bottom) and dimensions (width, height) of each individual plot. However, this sort of specification is unintuitive and, especially for simple arrangements, inconvenient and inefficient. This article describes a mechanism for specifying an arrangement of plots by constructing a matrix of plot names. The mechanism is intuitive, simple and, with the help of a few additional parameters, can produce quite sophisticated arrangements. The mechanism was developed as part of a prototype software package, but it does not rely heavily on any of the features of that package and it could be implemented in any statistical system.

Using bioconductor package BiGGR for metabolic flux estimation based on gene expression changes in brain

Predicting the distribution of metabolic fluxes in biochemical networks is of major interest in systems biology. Several databases provide metabolic reconstructions for different organisms. Software to analyze flux distributions exists, among others for the proprietary MATLAB environment. Given the large user community for the R computing environment, a simple implementation of flux analysis in R appears desirable and will facilitate easy interaction with computational tools to handle gene expression data. We extended the R software package BiGGR, an implementation of metabolic flux analysis in R. BiGGR makes use of public metabolic reconstruction databases, and contains the BiGG database and the reconstruction of human metabolism Recon2 as Systems Biology Markup Language (SBML) objects. Models can be assembled by querying the databases for pathways, genes or reactions of interest. Fluxes can then be estimated by maximization or minimization of an objective function using linear inverse modeling algorithms. Furthermore, BiGGR provides functionality to quantify the uncertainty in flux estimates by sampling the constrained multidimensional flux space. As a result, ensembles of possible flux configurations are constructed that agree with measured data within precision limits. BiGGR also features automatic visualization of selected parts of metabolic networks using hypergraphs, with hyperedge widths proportional to estimated flux values. BiGGR supports import and export of models encoded in SBML and is therefore interoperable with different modeling and analysis tools. As an application example, we calculated the flux distribution in healthy human brain using a model of central carbon metabolism. We introduce a new algorithm termed Least-squares with equalities and inequalities Flux Balance Analysis (Lsei-FBA) to predict flux changes from gene expression changes, for instance during disease. Our estimates of brain metabolic flux pattern with Lsei-FBA for Alzheimer’s disease agree with independent measurements of cerebral metabolism in patients. This second version of BiGGR is available from Bioconductor.

InfoVis and Statistical Graphics: Comment

The main points of Gelman and Unwin’s discussion article are uncontroversial. Yes, statistical graphics and infographics have different goals. Yes, statistical graphics people have an unfortunate tendency to make boring ugly graphs, while infographics people have an unfortunate tendency to trample on the principles of clear communication. Yes, both sides could learn from each other. And a good way for both sides to learn from each other is to have a discussion like this. But a discussion relies on two things: both sides have to talk to each other and both sides have to listen to each other. Perhaps the issue is that not all of these things have been happening.

Beer Tasting and the Problem of Coincidences

This article describes a matching problem. Given k unlabelled items and k labels, how hard is it to correctly match the labels to the items? The problem is an example of a very old one known as the problem of coincidences, which was originally motivated by a game played in the 18th century.

An Accessible Interaction Model for Data Visualisation in Statistics

Data is everywhere and its communication and understanding is an important pre-requisite for the full participation of individuals in the information age. Good data visualisation is commonly used to great effect for the sighted world, but are practically useless to a blind audience. Blind people are at risk of being left behind if efforts are not made to improve the access to information that is not traditionally conveyed in text, whether that text be accessed in braille, audio, or a computer’s screen reading software. Our work aims to provide an accessible way for blind users to easily, efficiently, and most importantly accurately, explore and query the data contained in diagrams such as bar charts, box plots, time series, and many more. We employ the statistical software environment R not only as a means to generate accessible diagrams, but also as a way for blind users to directly interact with data in the same way as their sighted peers by supporting immediate data visualisation via screen reading and interactive exploration.

An ISCC-NBS Colour List for ‘roloc’

To read the downloaded report unzip the contents to a directory and open the roloc-nbs.html file.