Visualization of Skewed Data

Abstract

After discussing the main characteristics of the histogram and of a number of variations in the boxplot, this work presents a visualization tool specifically tailored to deal with skewed data. The idea is to use various types of boxplots (the classical one, which is tuned for skewness of the data, the shifting boxplot, and the box-percentile plot), the violin plot, and the histogram with a nonparametric estimate of the density overlay. The plots are presented in such a way that they facilitate the extraction of additional information from each one. We show that a good deal of information can be extracted from the inspection of the output using example data from synthetic aperture radar images. We provide an implementation in R based on functions already available.Key words: Exploratory Data Analysis, Skewed Data, Boxplot, Violin Plot, Visualization. ResumenDespués de discutir las principales características del histograma y de un número de variables en el boxplot, se presento una herramienta de visualisación específicamente diseñada para el tratamiento de datos. La idea es usar varios tipos de boxplots (el clásico, el cual es adaptado para la consideración de sesgo de los datos, el boxplot trasladado, y el gráfico de cajas de percentiles), el gráfico violin, y el histograma con un estimador no paramétrico de la densidad. Los gráficos son presentados de forma que faciliten la extracción de información adicional. Se muestra como una buena cantidad a Professor. E-mail: rayospina@gmail.com b MSc Candidate. E-mail: amlarangeiras@gmail.com c Professor. E-mail: acfrery@gmail.com 400Raydonal Ospina, Antonio Marcos Larangeiras & Alejandro C. Frery de información que puede ser extraída a través de ejemplos de imágenes de radar de apertura sintética. Se presenta su implementacón en R basada en funciones actualmente disponibles.Palabras clave: análisis exploratorio de datos,boxplot, datos sesgados grá-ficos de violin, visualización.

Dynamic Data Visualizations to Enhance Insight and Communication Across the Life Cycle of a Scientific Project

“…Interactive visualizations provide an easy way to address queries in an immediate manner without the need for additional visualizations and thus can greatly streamline this process. In many cases, interactivity can also provide the means to transparently disclose the impact of analytical choices in statistical analysis (Ospina et al, 2014) and could serve as a valuable tool to teach statistical concepts to trainees (Xie, 2013).…”

Dynamic Data Visualizations to Enhance Insight and Communication Across the Lifecycle of a Scientific Project

“…Interactive visualizations provide an easy way to address queries in an immediate manner without the need for additional visualizations, and as such can greatly streamline this process. In many cases, interactivity can also provide the means to transparently disclose the impact of analytical choices in statistical analysis (Ospina et al, 2014) , and can serve as an invaluable tool to teach statistical concepts to trainees (Ellis & Merdian, 2015;Xie, 2013) .…”

The visualisation of data in a digital context

“…[ Figure 3: An interactive dashboard that provides a range of visualisaion and analysis options (Ellis & Merdian, 2015)] In response to the digitalisation of psychological research methods, data figures have and will continue to evolve in order to maximise their expressive power, both with regards to conveying the content and structure of the data as well as informing the analysis process (Campitelli & Macbeth, 2014;Marmolejo-Ramos, 2014). So far, this has included computational developments, such as the expansion of boxplots to include information about both distribution and density of the data (Marmolejo-Ramos & Matsunaga, 2009;Marmolejo-Ramos & Tian, 2010) or explorations of different data visualisations for particularly skewed data sets (Ospina et al, 2014).…”