Introduction to R

This article assumes you have gone through Why learn to code? and the introduction to SQL. SQL pulls data out of the database; R then takes over to analyse it.

Why R in clinical research

R was created by and for statisticians. That explains its popularity in healthcare:

• Statistical methods (tests, regressions, survival models…) are available natively or through proven libraries.
• The charts it produces are of excellent quality and widely accepted in scientific journals.
• It is often the language taught in medicine and public health, and therefore the one your future colleagues and supervisors use.

RStudio, the working environment

You almost never write R “bare”. You use RStudio, a free application that gathers in a single window the code editor, the console that runs commands, the charts and the help. That is where you will spend all your time.

The tidyverse: filtering and transforming

The tidyverse is a set of libraries that makes R readable for beginners. Its central library, dplyr, provides a small vocabulary of verbs matching the SQL moves: filter() (filter rows), select() (choose columns), group_by() + summarise() (aggregate).

You chain them with the pipe |>, read as “then”: take the data, then filter, then group…

library(dplyr)

# From a `patients` table (person_id, sex, age, creatinine)
patients |>
filter(sex == "F", age > 65) |>      # then: keep women over 65
group_by(sex) |>                     # then: group by sex
summarise(
  n = n(),                           # number of patients
  mean_creat = mean(creatinine, na.rm = TRUE)  # mean creatinine
)

If you read the SQL article, you recognise the logic: it’s the same reasoning — filter, group, summarise — in a different syntax. The na.rm = TRUE option asks R to ignore missing values when computing the mean, a point covered in the article on data quality.

Visualising with ggplot2

ggplot2, another pillar of the tidyverse, builds a chart in layers: you declare the data, what goes on the x and y axes, then the type of plot.

R

library(ggplot2)

ggplot(patients, aes(x = age, y = creatinine)) +
geom_point() +                       # a scatter plot
geom_smooth(method = "lm") +         # a linear trend
labs(
  title = "Creatinine by age",
  x = "Age (years)",
  y = "Creatinine (µmol/L)"
)

Result

Each + adds a layer. You get a clean figure in a few lines, ready to export for a paper or a presentation.

head(patients)      # the first rows
summary(patients)   # min, max, mean, missing values per column
nrow(patients)      # number of rows

Resources to learn

R and Linkr

The statistical analyses you design in the Study Designer — defining a population, computing variables — correspond to what you would do in R after extraction. Understanding R lets you extend an analysis beyond what a point-and-click tool offers, and verify your results.