Exploratory data analysis and visualisation

Exploratory data analysis (EDA) is a critical (and sometimes under-appreciated!) step that precedes statistical analysis. This includes steps like calculating descriptive statistics, finding extreme values, and summarizing the data -- in general, getting familiar with your raw data before you start to apply a statistical model! In this workshop, we will use dplyr (tidyverse) commands, like group_by() and summarize(), to highlight these important EDA steps.

EDA also includes graphing raw data to assess initial trends. The workshop will also cover different kinds of data visualisations, including box plots, scatterplots with trend lines, and bar plots with the ggplot package. The focus will be on quickly deploying informative graphs and selecting the right geom()s for the data types you have.

No previous knowledge is assumed, just general experience with R (loading packages, reading in data, etc.). If you'd like to polish up your tidyverse skills before joining, check out our previous workshop on data wrangling: https://youtu.be/NRgdTaAfwTo