Open access · free PDF · interactive playground
FROM DATA TO THESIS
Using R for Non-Technical
Follow one Master's thesis from a messy survey export to results that can be defended. Every method in the book answers one of the study's research questions, so you learn R the way you will use it: on a real research project.
The book in numbers
How every chapter works
The same five steps, so you always know where you are.
A research question
Each chapter starts with a question from the case-study thesis, such as "Does the wellbeing workshop help?"
A tiny example
The new idea is shown on a handful of numbers, so you can see exactly what it does.
The case-study data
The same tool is applied to the real case study, and you learn how to report the result in a thesis.
In your field
A short box shows the same method in health, agriculture, or business research.
Practise
Exercises in the playground: in your browser, or as a project to download and open in RStudio.
Learning paths
Start where you are.
The complete path
All chapters in order, from installing R to presenting your results.
Coming from SPSS
See how familiar tasks map to R, import your SPSS files with their labels, then move on to Part 2.
Statistics for your thesis
Parts 1 and 2: describing data, hypothesis tests, ANOVA, regression, and mixed models.
Towards machine learning
Part 3: prediction, classification, clustering, neural networks, and forecasting.
The arc of the book
Foundations
R and RStudio, data structures, cleaning and reshaping a messy survey export, and your first plots.
Statistical analysis for research
Research questions and hypotheses, describing data, hypothesis tests, ANOVA and regression, questionnaire scales, and change over time.
Machine learning with R
Predicting who might drop out, finding student profiles, neural networks, and forecasting.
Reproducible research and applications
Quarto reports, Shiny dashboards, using AI tools responsibly, and a complete project from raw data to thesis chapter.
Tools you will use
All free and open source.
Get the data
The student wellbeing data comes as ordinary files and as an R package. The book teaches both.
Install the package from this website:
install.packages("https://polla.dev/data2thesis_r/downloads/data2thesis_1.1.0.tar.gz",
repos = NULL, type = "source")
library(data2thesis)
head(students)Or download the package file and the data files on GitHub.
Please note: the case study and its data are fictional: the data was generated by a computer program to look realistic, and its patterns were built in by the author. It describes no real people and is not evidence about real students; do not cite or use it as research findings.
Frequently asked questions
What is this book about? (Full back-cover description)
Turn messy data into a defended, publication-ready thesis.
For many postgraduate and academic researchers, collecting data is only the beginning of the real challenge. The hardest hurdle is turning spreadsheets, surveys, and lab observations into robust statistical models and defendable written arguments. Commercial point-and-click tools leave your analysis opaque, while standard programming textbooks bury you in abstract computer science theory.
From Data to Thesis bridges that divide. Written specifically for graduate students, doctoral researchers, and academic professionals, this book provides a complete, modern roadmap for empirical research using R. Rather than abstract mathematics, every concept is taught through a single, realistic running case study following 600 students across four semesters.
Every chapter guides you through five clear steps:
- A Concrete Research Question — Rooted in authentic academic inquiry.
- A Minimal Working Example — To build immediate, intuitive understanding.
- The Case-Study Analysis — Applied data cleaning, visualization, and modeling.
- In Your Field — Transferable applications across healthcare, social sciences, agriculture, and business.
- Thesis Reporting & Interpretation — The exact wording, tables, and APA-style figures you need for your final draft.
From exploratory data analysis and hypothesis testing to mixed-effects models, machine learning, time-series forecasting, and ethical AI assistance, this book gives you the tools, code, and confidence to defend your research with scientific rigor.
Inside you will discover:
- How to clean, reshape, and visualize complex data using modern tidyverse workflows.
- How to choose the right statistical test—and how to diagnose and fix common assumption violations.
- Practical machine learning and predictive modeling without the computational overwhelm.
- Reproducible research workflows using Quarto that generate thesis-ready tables and figures.
- Interactive browser playgrounds to practice every method without installing a single package.
Whether you are writing your first Master’s dissertation, completing your doctoral defense, or preparing an empirical journal article, this book is your desk companion from raw data to submitted thesis.
Do I need to know programming or statistics?
No. The book starts from zero and explains every term when it first appears. Each new idea is shown first on a tiny example before it is used on real data.
Is the data real?
No. The student, her study, and her data are fictional. The data was generated by a computer program to look like a realistic survey of graduate students, so that every method in this book has something to find. It describes no real people, and its patterns (for example, that the workshop raised wellbeing, or that students who sleep more have higher grades) were built into the program by the author, not discovered. Nothing in this book is evidence about the wellbeing of real students, and the data and results must not be cited or used as findings about students, universities, or any real situation. The same applies to the counselling service's records and to the students' written answers. It was designed so that every method in the book finds something worth interpreting, including some honest "no effect" results. The script that generates it is published, so anyone can check or regenerate it.
My research is not in education. Is the book for me?
Yes. The methods are the same in every field. "In your field" boxes in each chapter show the same method on real data from health, agriculture, and business research.
Do I need to install anything to start?
Not for the playground: its exercises run in your browser. To follow the book on your own computer you will install R and RStudio, and Chapter 1 shows you how.
Does it cover AI tools?
Yes. Chapter 18 shows how to use AI assistants to write and check R code, how to analyse open-ended answers with a language model, and how to use AI responsibly in research.