Statistics initiation with the free R software : make your first visualizations with the ggplot2 package

Abstract

Editor’s note: The main purpose of the RDPLF (French Language Peritoneal Dialysis and Home Hemodialysis Registry) is to help physicians and nurses, caring for patients treated by home dialysis, to evaluate their clinical practices and also to conduct studies based on anonymous exports of the data base . To this end, since June 2019, a series of training articles on the use of free R-software is published quarterly with each issue of the Bulleti, de la Dialyse à Domicile. The goal is to allow all teams to perform basic statistics and quickly visualize their data.

The first article in this tutorial was devoted to downloading and installing R software on Macintosh and PC computers: https://doi.org/10.25796/bdd.v2i2.20513.

The second article was devoted to graphical visualization of statistical data with the Esquisse package, easy to use and requiring little learning: https://doi.org/10.25796/bdd.v2i3.21313

This third article is devoted to this ggplot2 package and requires a learning effort, but it allows the realization of many types of visualizations, with renderings that can be of very high quality, and thus directly usable in publications.

As in the previous issues, an example file, taken from the RDPLF database will be used.

Claire Della Vedova is an engineer in biostatistics / data analyst, she daily uses the software R to analyze data. She has worked for more than 15 years in the fields of environment and health, and has trained many students and researchers in the use of R. She runs since November 2017 the blog Statistics and Software R whose goal is to help beginners to better understand the standard statistical methods and to use the R software more effectively, especially through tutorials: https://statistique-et-logiciel-r.com/.