R for journalists

With R you can analyse large, messy, or recurring datasets faster and better than in a spreadsheet.

‍In this practical training you learn to program with R and RStudio to find, clean, merge, analyze, and visualize data — always starting from journalistic questions.

Target audience

This training is designed for journalists, researchers, and data journalists who want to analyze larger or more complex datasets, as well as for professionals who want to make their analyses reproducible without depending on manual spreadsheet work. It is also well suited to journalists who regularly combine data from multiple sources, collect data online, or want to repeat analyses whenever new figures become available.

The training is designed for beginners in R; no programming experience is required, although some experience with spreadsheets and basic concepts such as rows, columns, and variables is helpful.

What you will learn

• Working with R and RStudio: creating projects, writing scripts, installing packages, and importing datasets.
• Documenting your research work in an R Notebook, where question, working notes, code, tables, and graphs come together.
• Importing, exploring, and exporting CSV and Excel files.
• Searching datasets with the key Tidyverse functions, such as filtering, selecting, sorting, grouping, counting, and summing.
• Joining data based on a common key, even when working with more than two datasets.
• Cleaning data: correcting column names and data types, removing duplicates, handling missing values, standardizing text, processing dates, and splitting or merging fields.
• Asking journalistic questions of data: how big is a problem, who is at the top, what is exceptional, how is something distributed, what is changing, and what data is missing?
• Using descriptive statistics for totals, averages, medians, spread, outliers, shares, and trends.
• Analyzing correlations and regression, with attention to the crucial limitation that correlation does not prove causation.
• Creating static graphs with ggplot, including bar, line, scatter, and box plots.
• Scraping data from one or more web pages with R.
• Writing workable, readable scripts that you can repeat, adapt, share, and check.

Structure

• The training follows the journalistic data workflow: from research question and raw data to a verifiable finding and visualization.
• You start with an R project: one organized working environment where datasets, code, notes, and results come together.
• Next, you learn to load data, check its structure, and explore which variables, values, and gaps the dataset contains.
• After that, you process the data with short, understandable Tidyverse commands.
• You combine datasets, perform analyses, and translate the results into journalistic angles.
• Finally, you create graphs and record your approach in a Notebook or script, so the analysis is reproducible.
• You work with journalistically relevant practice data, including on industrial emissions, climate, and public data.

Teaching method

You will get clear, step-by-step explanations without unnecessary technical jargon, combined with short coding exercises directly tied to journalistic questions. You'll work in RStudio with the Tidyverse, a collection of tools that makes R more accessible for data journalists, and see demonstrations of importing, cleaning, joining, analyzing, visualizing, and scraping data. You'll practice with ready-made code examples that you'll learn to read, adapt, and apply to your own datasets, and work in an R Notebook where you combine research notes, code, and results. There's also room to discuss your own research questions and datasets and, where possible, use them as practice material.

Duration

‍The training can be offered as a short introduction, a multi-day course, or an in-company program. The exact duration, schedule, and emphasis on components such as analysis, visualization, scraping, or data cleaning are tailored to the participants' prior knowledge and needs.

‍Outcome

‍Afterward you will be able to:

• Set up your own R project and an organized working environment in RStudio.
• Import, explore, and export datasets from CSV and Excel files.
• Quickly filter, sort, group, and summarize large datasets.
• Safely and verifiably join multiple datasets.
• Clean raw data and prepare it for analysis.
• Find journalistic patterns: rankings, trends, anomalies, ratios, and statistical relationships.
• Collect online data from web pages with R.
• Create and customize appropriate graphs.
• Document your entire analysis in reusable code and a readable Notebook.
• Carry out complex data investigations faster, more transparently, and more reproducibly than with spreadsheets alone.