An introduction to Bayesian statistics

Bayesian statistics is everywhere: weather forecasting, epidemic analysis, biodiversity conservation… In an uncertain world, it helps us estimate, predict, and make decisions by giving meaning to data. This book offers an accessible and practical introduction to Bayesian statistics. The author explains, step-by-step, the fundations of the approach, its advantages, and the logic underlying Bayesian reasoning. Learning is built around the free software R and develops through research questions related to the ecology of the coypu, which serves as the book's guiding thread. Each chapter addresses a key pillar: Bayes' theorem, Markov chain Monte Carlo (MCMC) methods, the choice and role of prior distributions, linear regression and its extensions, generalized linear models (mixed or not), and finally model comparison and validation. Readers are invited to code, simulate, test, and visualize in order to understand, supported by worked examples and online materials. Written in a clear and engaging style, like a dialogue between teacher and student, the book demystifies Bayesian statistics. It is intended for anyone wishing to learn this approach, particularly those working in the life sciences, data science, or environmental sciences.