What is R and Why Should We Use It?

Mark Andrews

What is R?

  • R is a free, open-source computing environment designed for statistics, data analysis, and graphics
  • Started in the early 1990s as an academic project in New Zealand, based on an earlier language called S
  • By the early 2000s it had spread across statistics departments worldwide
  • Today it is used in government agencies, NGOs, finance, tech companies, and across academic research

Free and open source

  • R costs nothing: no licence fees, no free-versus-paid tiers, no vendor lock-in
  • Released under the GNU General Public Licence — guaranteed to remain freely redistributable forever
  • No company can buy it and restrict access or charge for it
  • Runs on Windows, macOS, Linux, from a laptop to a supercomputer cluster
  • No tracking, no ads, no platform lock-in: the same script runs anywhere

A power tool for data analysis

  • Out of the box: linear models, ANOVA, time-series, high-quality graphics, data manipulation
  • Over 22,000 packages on CRAN — there is almost certainly a package for whatever you need
  • New statistical methods published in journals are routinely implemented in R first
  • Built for incremental learning: a small core gets you far; expand on demand

Widely used

  • Consistently in the top 10 most popular programming languages worldwide (Tiobe, Redmonk, PYPL)
  • Used by millions of analysts, researchers, and data scientists every week
  • The CRAN package repository has grown at roughly 13–14% per year since 2015 — from 6,000 to 22,000+ packages
  • Major users include the NHS, ONS, Bank of England, pharmaceutical companies, and most research universities

Command based (and that’s right)

  • R is operated by typing commands — the same model used by Stata, SAS, MATLAB, and Python
  • These are not legacy tools: the command interface is still the right interface for power tools
  • GUIs are easy for simple one-off tasks; the moment you need to recode 200 survey items, merge files, or reshape a dataset, endless manual clicking becomes the bottleneck
  • A short R script handles those chores in one pass, and the script is a permanent, shareable, rerunnable record of exactly what was done
  • This is professional software for professionals — not a household appliance
⌂