Software overview

Software is ever-changing - programs which were the standard 20 years ago may now be a distant memory. The purpose of this chapter is to briefly summarize the main advantages of select state of the art statistical modelling1 software, that you are likely to encounter in most fields of industry and academia. In a later chapter we provide the steps necessary to install such software via a docker container. Another important point to mention is that the software that we cover is free to use, meaning that you can use it both in and outside of academia.

We also present a number of alternative statistical software, some of which are emerging new alternatives (such as Julia), while others have a broader scope than just data science (such as Matlab, or Octave). Although a number of the alternative software is quite expensive for commercial use.

  1. In these notes we use terms like statistical modelling, machine learning, data science and data analysis interchangeably. For example, linear and logistic regression models are classic examples of statistical models, yet can be found in many machine learning and data science literature.↩︎