In this 3h. session we take an overview of the main ideas behind making your
data analysis reproducible and transparent. For that, we use the
statistical platform, likely the most popular choice among academia and
industry, as the main tool.
We begin with the main ideas behind a reproducible approach to data analysis, provide some background on the history of R and use a popular replication example to show how to read, manipulate, interact, analyze, visualize and write your data. In particular, we use the famous Reinhart and Rogoff replication exercise by Thomas Herndon et al.
To follow on this session on your own machine, you will need both
RStudio installed. For links to download and install them, head over to
the Requirements page to see how to install them if
you haven’t yet.
No previous background on
R or any specific statistical background is needed
for this session, although some basic understanding of statistics and data (at an
undergraduate level) is required to comfortably follow along.
After completing the session, you should be able to:
Ris, how it was created and what are its main strengths
Rpackages and learn to use them through different ways of accessing help and support for them
Rusing several formats
R, including calculating descriptive measures and running a regression
Reinhart & Rogoff: