PLOTCON 2016: Haley Jeppson, Visualizing Multivariate Categorical Data скачать в хорошем качестве

PLOTCON 2016: Haley Jeppson, Visualizing Multivariate Categorical Data

Visualizing multidimensional data can be cumbersome. There is a subtle complexity that arises from the hierarchical structure of the counts and proportions that are important for understanding the multivariate discrete distributions. In addition, the options of graphical methods for categorical variables are not well developed in comparison with what is available for numeric variables. One method of visualizing multidimensional data is through a mosaic plot. Mosaic plots can be an easy and powerful option for identifying relationships between multiple variables. However, while mosaic plots have been implemented in a variety of packages, the ordinary grammar of graphics does not support mosaic plots. With the R package ggmosaic, a custom ggplot2 geom designed for mosaic plots is implemented. In addition, ggmosaic creates plots that can be converted into interactive plotly graphs. In this talk, I'll present examples that highlight the versatility and ease of use of ggmosaic while demonstrating the practicality of mosaic plots. Haley is a PhD student in the Department of Statistics at Iowa State University. Her primary research interests are visual inference, statistical graphics, and statistical computing. Haley’s current work includes the R package ggmosaic which has the capability of creating interactive mosaic plots in the ggplot2 framework.